© 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. 15-RESID-POST-AA
    11. 39658
    Prev
    Next
    INDEX
    Explanations

    government legislative bodies

    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
     счита
    -0.07
    流感
    -0.07
    iven
    -0.07
    ˁ
    -0.06
    alculate
    -0.06
    此次
    -0.06
    宝鸡
    -0.06
    localctx
    -0.06
    年前
    -0.06
    ENABLE
    -0.06
    POSITIVE LOGITS
     conspicuous
    0.07
     FALSE
    0.07
    responses
    0.07
    oundary
    0.07
    ,str
    0.07
    浴
    0.07
    /connect
    0.07
     נדר
    0.07
    מול
    0.07
     dwóch
    0.07
    Activations Density 0.006%

    No Known Activations