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. 36332
    Prev
    Next
    INDEX
    Explanations

    Ketogenic/low-carb diet

    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
    placed
    -0.07
    Russia
    -0.07
    𝕒
    -0.07
     locked
    -0.07
    /mark
    -0.07
    covering
    -0.06
    Italic
    -0.06
     liquid
    -0.06
    Α
    -0.06
    音响
    -0.06
    POSITIVE LOGITS
    _init
    0.07
    >>>>
    0.07
    不在乎
    0.07
    scientific
    0.07
     Programm
    0.06
     sond
    0.06
    vester
    0.06
     handicap
    0.06
    形成了
    0.06
    _dept
    0.06
    Activations Density 0.006%

    No Known Activations