© 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. 14-TRANSCODER-HP
    7. 40651
    Prev
    Next
    INDEX
    Explanations

    Actions or beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺĻ
    -0.34
    imu
    -0.26
    ymes
    -0.26
    ushman
    -0.25
    æİ
    -0.25
    stdin
    -0.24
     Fits
    -0.24
    æīª
    -0.23
    ãĥ¯ãĥ¼ãĤ¯
    -0.23
    å¡ħ
    -0.23
    POSITIVE LOGITS
    notated
    0.28
    agers
    0.27
    岬
    0.26
     /*#__
    0.26
    以为
    0.26
    DbContext
    0.25
     either
    0.25
    è¡ħ
    0.25
    ully
    0.25
    arf
    0.24
    Activations Density 0.197%

    No Known Activations