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. 71653
    Prev
    Next
    INDEX
    Explanations

    Monads (programming)

    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
    _ll
    -0.07
    .Usuario
    -0.07
    _enc
    -0.07
     renal
    -0.07
    .Timeout
    -0.06
     elective
    -0.06
    这也是
    -0.06
    =torch
    -0.06
    kj
    -0.06
    dration
    -0.06
    POSITIVE LOGITS
    .ALIGN
    0.06
    一等奖
    0.06
    与众不同
    0.06
    Ò
    0.06
    帜
    0.06
    青山
    0.06
    젝
    0.06
     מבוס
    0.06
     أثن
    0.06
    ikes
    0.06
    Activations Density 0.007%

    No Known Activations