© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16791
    Prev
    Next
    INDEX
    Explanations

    money

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of earning or making money and passages about ways to generate financial income (especially in online contexts).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ney
    -0.07
    អ
    -0.07
     camper
    -0.07
    🇳
    -0.07
    讧
    -0.07
    .promise
    -0.07
     ComponentFixture
    -0.07
     faces
    -0.06
    	FILE
    -0.06
     المتعل
    -0.06
    POSITIVE LOGITS
    roadcast
    0.07
    .contentType
    0.07
    usement
    0.07
     throughput
    0.07
    licit
    0.06
    單
    0.06
    aría
    0.06
    	audio
    0.06
    幽
    0.06
    散
    0.06
    Activations Density 0.042%

    No Known Activations