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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 72426
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    (",");↵
    -0.07
     worlds
    -0.07
    推
    -0.07
     mods
    -0.07
    wap
    -0.07
     제
    -0.07
     Washer
    -0.07
    uder
    -0.07
    ップ
    -0.06
    作文
    -0.06
    POSITIVE LOGITS
     succinct
    0.07
    ISED
    0.07
    _FACE
    0.07
    �
    0.07
    ưới
    0.07
     Crest
    0.07
    一个小
    0.07
    𝔱
    0.07
    .Payment
    0.07
    CTL
    0.07
    Activations Density 0.001%

    No Known Activations