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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    11. 25318
    Prev
    Next
    INDEX
    Explanations

    Units and measurements

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mao
    -0.07
    ﾖ
    -0.07
     совершен
    -0.07
     реж
    -0.07
    sitemap
    -0.07
    走出去
    -0.06
     Bombay
    -0.06
    遍
    -0.06
    ביצ
    -0.06
    ByteArray
    -0.06
    POSITIVE LOGITS
     tray
    0.07
    ctype
    0.07
    rv
    0.07
    (atom
    0.07
    支架
    0.07
    boats
    0.07
     sscanf
    0.07
    rm
    0.07
    (evt
    0.07
    ёт
    0.07
    Activations Density 0.115%

    No Known Activations