© 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. 40934
    Prev
    Next
    INDEX
    Explanations

    de

    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
    edly
    -0.28
    èijµ
    -0.28
    anie
    -0.27
    ziel
    -0.27
    erator
    -0.26
     dramas
    -0.26
    ãĤīãģļ
    -0.26
    åı¯çĪ±
    -0.25
    éĨ¯
    -0.25
    说æĺ¯
    -0.25
    POSITIVE LOGITS
     phy
    0.26
    约åįł
    0.26
    ought
    0.25
    çļĦä»·åĢ¼
    0.25
    对æłĩ
    0.25
    èĤĽ
    0.24
    ounter
    0.24
    egrity
    0.24
    @brief
    0.23
    çļĦæł·åŃIJ
    0.23
    Activations Density 1.558%

    No Known Activations