© 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. 24-TRANSCODER-HP
    7. 150496
    Prev
    Next
    INDEX
    Explanations

    Documentation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ington
    -0.31
    worthy
    -0.28
    eten
    -0.27
    naissance
    -0.26
    éĺ¿å§¨
    -0.25
    -rise
    -0.24
    ponder
    -0.24
    KN
    -0.24
    两项
    -0.24
     Included
    -0.23
    POSITIVE LOGITS
     Chap
    0.26
    ç¡®
    0.26
    hal
    0.25
    opcode
    0.24
    zac
    0.24
     Uph
    0.24
     Flo
    0.24
    vecs
    0.24
    ä¸į让
    0.24
    ắng
    0.24
    Activations Density 0.153%

    No Known Activations