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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42119
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ving
    -0.27
    èIJ¥åħ»
    -0.27
     LICENSE
    -0.27
     dedic
    -0.27
    vn
    -0.25
    edelta
    -0.25
    agine
    -0.24
    ãģĹãģ¦ãģĦãģ¦
    -0.24
    秦çļĩ
    -0.24
    æİ¥
    -0.24
    POSITIVE LOGITS
     Te
    0.29
    artin
    0.27
    TÄ°
    0.25
    TRIES
    0.25
    flutter
    0.25
    æķĻç¨ĭ
    0.24
    æ»´
    0.24
     gegenüber
    0.24
     Äij
    0.24
     TE
    0.24
    Activations Density 0.005%

    No Known Activations