© 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. 40390
    Prev
    Next
    INDEX
    Explanations

    JSON

    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
    Datum
    -0.32
     Subway
    -0.26
    uran
    -0.26
    ermann
    -0.26
    datum
    -0.25
    SHOT
    -0.25
    ä¸įåı¯éģ¿åħį
    -0.25
    åħ¸ç¤¼
    -0.24
    manifest
    -0.24
    Tube
    -0.24
    POSITIVE LOGITS
    çĤİçĹĩ
    0.28
     infl
    0.28
    ä¾Ŀæ³ķ
    0.26
    åºĵ
    0.26
    inflate
    0.25
    ä¸İåħ¶
    0.25
    /vnd
    0.24
    _FS
    0.24
    çŃīåIJĦç§į
    0.24
    çŃīå¤ļç§į
    0.24
    Activations Density 3.535%

    No Known Activations