© 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. 40764
    Prev
    Next
    INDEX
    Explanations

    Oil and acronyms

    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
    æĶ¾å¤§
    -0.29
    æ¡Ī
    -0.28
    çģŃ
    -0.27
    .mozilla
    -0.27
     IonicPage
    -0.26
     pent
    -0.25
    .python
    -0.25
    åħ¸
    -0.25
     Wo
    -0.25
    è¿Ļæĸ¹éĿ¢
    -0.25
    POSITIVE LOGITS
     genu
    0.29
    íij¸
    0.27
    rze
    0.27
     redistributed
    0.26
    antz
    0.25
    pped
    0.24
    iffs
    0.24
    aty
    0.24
    sty
    0.24
    æ±Łå±±
    0.24
    Activations Density 0.996%

    No Known Activations