Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36586
    Prev
    Next
    INDEX
    Explanations

    Forum/blog posts

    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
     regained
    -0.07
    ujących
    -0.07
    halt
    -0.07
    .Fire
    -0.07
     favourites
    -0.07
     retVal
    -0.07
    fu
    -0.07
     יוצא
    -0.07
     timedelta
    -0.07
    Budget
    -0.07
    POSITIVE LOGITS
    团伙
    0.07
     bloque
    0.07
    .mac
    0.06
    mall
    0.06
    onso
    0.06
    混淆
    0.06
    ”,
    0.06
    UBLIC
    0.06
    苟
    0.06
    .Hex
    0.06
    Activations Density 0.137%

    No Known Activations