© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 52608
    Prev
    Next
    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    腕
    -0.07
     aph
    -0.07
     Wil
    -0.07
     Glo
    -0.07
     woodland
    -0.06
    :e
    -0.06
     ue
    -0.06
     innovation
    -0.06
    落叶
    -0.06
     Escort
    -0.06
    POSITIVE LOGITS
     같습니다
    0.07
     UserProfile
    0.07
     spriteBatch
    0.07
     свой
    0.07
    ┏
    0.07
     перв
    0.07
    UserProfile
    0.07
     RIGHTS
    0.07
    刚开始
    0.06
    refresh
    0.06
    Activations Density 0.000%

    No Known Activations