© 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. 20-TRANSCODER-HP
    7. 108054
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arine
    -0.33
    ogen
    -0.29
    ExecutionContext
    -0.29
    emean
    -0.28
     Interior
    -0.27
    åĽŀ头
    -0.25
    amac
    -0.25
    å¥Ķ
    -0.24
    emain
    -0.24
    olin
    -0.24
    POSITIVE LOGITS
    .lu
    0.28
    lion
    0.25
    (rt
    0.25
    plr
    0.24
    åı¤ä»Ĭ
    0.24
    .bootstrap
    0.24
    /gtest
    0.24
     harmonic
    0.23
    andles
    0.23
    ноÑģÑĤ
    0.23
    Activations Density 0.234%

    No Known Activations