© 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. 51645
    Prev
    Next
    INDEX
    Explanations

    Business and law

    np_max-act · gemini-2.0-flash

    names of industries, legal practice areas, and business/sector terms.

    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
     bảo
    -0.07
    ni
    -0.07
     provision
    -0.07
    ½
    -0.07
    词
    -0.07
    泓
    -0.07
    損
    -0.07
    训
    -0.06
     ★
    -0.06
    资产评估
    -0.06
    POSITIVE LOGITS
    肤色
    0.08
    מקומות
    0.08
     accomp
    0.07
    archical
    0.07
    	writel
    0.07
    iami
    0.07
    笆
    0.07
    sigmoid
    0.07
    飏
    0.07
    (sync
    0.07
    Activations Density 0.030%

    No Known Activations