© 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. 1436
    Prev
    Next
    INDEX
    Explanations

    URLs with images

    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
    -contained
    -0.07
    솎
    -0.07
    糕
    -0.07
    印章
    -0.07
    薹
    -0.07
    燔
    -0.06
     ###
    -0.06
    pure
    -0.06
    것
    -0.06
     Dios
    -0.06
    POSITIVE LOGITS
    _usr
    0.08
    甚么
    0.07
    /filter
    0.07
    _cf
    0.07
    _next
    0.07
    وتر
    0.07
    ทำความสะอาด
    0.06
     muttered
    0.06
    我和
    0.06
    多少钱
    0.06
    Activations Density 0.003%

    No Known Activations