© 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. 39999
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    .fit
    -0.29
    ôt
    -0.28
    æĤ¨å¥½
    -0.27
    åīįåIJİ
    -0.26
     ste
    -0.25
    éĹ´
    -0.24
     liter
    -0.24
    ä½ľèĢħæīĢæľī
    -0.24
    ots
    -0.24
    .snap
    -0.24
    POSITIVE LOGITS
    è¿Ķè¿ĺ
    0.29
    >Returns
    0.27
    zhou
    0.26
    enor
    0.25
    工夫
    0.25
    reon
    0.25
     Prescott
    0.24
     eben
    0.24
     lẫn
    0.24
    æī§æĶ¿
    0.23
    Activations Density 1.473%

    No Known Activations