© 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. 41347
    Prev
    Next
    INDEX
    Explanations

    variable

    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
    mö
    -0.29
    ninger
    -0.29
    æīĵæĸŃ
    -0.27
    ()._
    -0.25
    mise
    -0.25
    æĺ¯ä¸Ģç§į
    -0.25
    omba
    -0.24
     ÅĽrod
    -0.24
    ="__
    -0.24
    elist
    -0.24
    POSITIVE LOGITS
    代åĬŀ
    0.29
     advancement
    0.29
    大è¡Ĺ
    0.28
     Borough
    0.27
    éĵĽ
    0.27
    <HTML
    0.25
    Subview
    0.24
    ÑıÑĤи
    0.24
    çļĦæľĭåıĭ
    0.24
    duct
    0.24
    Activations Density 1.040%

    No Known Activations