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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 7881
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     qualified
    -0.07
     TER
    -0.07
    总觉得
    -0.07
    みんな
    -0.07
    na
    -0.07
     Ger
    -0.07
     chociaż
    -0.07
    ERICA
    -0.07
    ести
    -0.07
    ษา
    -0.07
    POSITIVE LOGITS
    _track
    0.07
    DSP
    0.07
    眠
    0.07
    Console
    0.07
    ؟
    0.06
    旅
    0.06
    _decoder
    0.06
     brains
    0.06
    ⇝
    0.06
    곽
    0.06
    Activations Density 0.028%

    No Known Activations