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. 31245
    Prev
    Next
    INDEX
    Explanations

    say period

    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
    ࡔ
    -0.07
     mosaic
    -0.07
    集团公司
    -0.07
    ෆ
    -0.07
    (blob
    -0.07
    (Transaction
    -0.06
    袄
    -0.06
    箜
    -0.06
     כאמור
    -0.06
    年度
    -0.06
    POSITIVE LOGITS
    ти
    0.08
    �
    0.07
    을
    0.07
    ror
    0.07
    жи
    0.07
    adt
    0.07
     venues
    0.07
    了
    0.07
    allen
    0.06
     Stones
    0.06
    Activations Density 0.256%

    No Known Activations