© 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. 40271
    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
    樽
    -0.29
    _PROFILE
    -0.24
    ainty
    -0.24
    ioni
    -0.24
     bid
    -0.24
    ç±ģ
    -0.24
     handleError
    -0.24
    åĬ¨
    -0.23
     welded
    -0.23
    vard
    -0.23
    POSITIVE LOGITS
    éĻĽ
    0.28
    /AFP
    0.27
    nish
    0.25
    æĸ°å½¢åĬ¿ä¸ĭ
    0.25
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.24
    gom
    0.24
     Snow
    0.24
     freel
    0.23
    游æĪıä¸Ń
    0.23
     GANG
    0.23
    Activations Density 0.050%

    No Known Activations