© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 974
    Prev
    Next
    INDEX
    Explanations

    navigate

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     roast
    -0.07
     Stable
    -0.07
    _dash
    -0.07
    dash
    -0.07
     Almost
    -0.07
    秋天
    -0.07
     prêt
    -0.06
     scrollTo
    -0.06
    lashes
    -0.06
     devoid
    -0.06
    POSITIVE LOGITS
     오�
    0.08
    汇率
    0.07
    LEAR
    0.07
     Г
    0.07
    влекатель
    0.07
    ய
    0.07
     medidas
    0.06
    �
    0.06
     cemetery
    0.06
    艴
    0.06
    Activations Density 0.012%

    No Known Activations