© 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. 61445
    Prev
    Next
    INDEX
    Explanations

    Sports reporting with ball movement

    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
     startActivity
    -0.08
     Splash
    -0.07
    izzlies
    -0.07
     Susan
    -0.07
     QString
    -0.07
     Moose
    -0.07
     variables
    -0.07
    раст
    -0.07
    _base
    -0.07
    Ra
    -0.06
    POSITIVE LOGITS
    荮
    0.07
    🔮
    0.07
    멜
    0.07
    手术
    0.07
    字体
    0.07
    📅
    0.07
    nin
    0.07
    𝘥
    0.07
    🤖
    0.07
    不方便
    0.06
    Activations Density 0.026%

    No Known Activations