© 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. 23-TRANSCODER-HP
    7. 25175
    Prev
    Next
    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    寻常
    -0.26
    社ä¼ļç»Ħç»ĩ
    -0.26
    åij¨è¾¹
    -0.25
     Salisbury
    -0.25
    kins
    -0.25
     favors
    -0.25
    vron
    -0.25
    sess
    -0.25
    tok
    -0.24
    sed
    -0.24
    POSITIVE LOGITS
    .ArgumentParser
    0.30
    ing
    0.29
     honestly
    0.27
    edImage
    0.26
     circ
    0.25
    iles
    0.25
    ated
    0.24
     rz
    0.24
    osc
    0.24
    Ñijн
    0.24
    Activations Density 0.073%

    No Known Activations