© 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. 40940
    Prev
    Next
    INDEX
    Explanations

    ibia

    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
    çĥĤ
    -0.29
    ampa
    -0.28
    åĪ¸
    -0.26
    Tac
    -0.25
    ä¸ļ
    -0.25
    å¥Ĥ
    -0.25
    ç«Ļéķ¿
    -0.25
    avo
    -0.24
    udd
    -0.24
    æ¼Ķç»İ
    -0.24
    POSITIVE LOGITS
    tures
    0.29
    _NB
    0.27
    åįģ足
    0.26
    æĺİå¹´
    0.26
    åľ°ä¸ĭæ°´
    0.26
    è·Łä½ł
    0.26
    èĩ³äºİ
    0.25
    饮
    0.24
    ront
    0.24
     <!--[
    0.24
    Activations Density 0.187%

    No Known Activations