© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151409
    Prev
    Next
    INDEX
    Explanations

    Code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    imers
    -0.28
    ä¸ĢæĬĬ
    -0.27
    计
    -0.26
    اÙħØ©
    -0.24
    æķĪ
    -0.24
    寻æ±Ĥ
    -0.24
    æ¿Ģ
    -0.23
    ä¸Ģ件
    -0.23
    еÑģÑĤв
    -0.23
    ä¸ĢéĿ¢
    -0.23
    POSITIVE LOGITS
     Clyde
    0.25
     erg
    0.24
    welcome
    0.24
    嶷
    0.24
     radians
    0.24
    auc
    0.24
    主é¢ĺæķĻèĤ²
    0.23
     Humb
    0.23
    okin
    0.23
    娥
    0.23
    Activations Density 0.969%

    No Known Activations