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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 59400
    Prev
    Next
    INDEX
    Explanations

    Software errors and retries

    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
    _co
    -0.07
    /us
    -0.07
    Trust
    -0.07
    .utf
    -0.07
    _buttons
    -0.07
    _REPLACE
    -0.06
     encode
    -0.06
     ومع
    -0.06
    Ú
    -0.06
    IFT
    -0.06
    POSITIVE LOGITS
    髌
    0.06
    当之无
    0.06
     Winnipeg
    0.06
    #!
    0.06
    _release
    0.06
    ,test
    0.06
    inerary
    0.06
    izont
    0.06
    spot
    0.06
    .D
    0.06
    Activations Density 0.021%

    No Known Activations