© 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. 41220
    Prev
    Next
    INDEX
    Explanations

    Fant

    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
    ï¸
    -0.29
     bathing
    -0.28
    é¢Ĩ导èĢħ
    -0.28
    udios
    -0.26
    ãĤ¨ãĥ«
    -0.26
    conscious
    -0.25
    unos
    -0.25
    å¥Ĺ
    -0.25
    yny
    -0.25
    undra
    -0.24
    POSITIVE LOGITS
    æĽ´é«ĺçļĦ
    0.27
    rices
    0.27
    å·
    0.27
     final
    0.26
    enus
    0.26
    -ul
    0.25
     antenna
    0.24
    çĭĻ
    0.24
    åĨł
    0.24
    Final
    0.24
    Activations Density 0.152%

    No Known Activations