© 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. 12-TRANSCODER-HP
    7. 23613
    Prev
    Next
    INDEX
    Explanations

    Ethiopia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨äº¬
    -0.28
    çģ«åĬĽ
    -0.25
    ä¾Ľæļĸ
    -0.25
    Behavior
    -0.25
    nox
    -0.24
    æĹıèĩªæ²»
    -0.24
     Lond
    -0.24
    ç½ijç»ľä¼łæĴŃ
    -0.24
    (Properties
    -0.24
    licit
    -0.24
    POSITIVE LOGITS
    ç°¿
    0.25
    sth
    0.25
    /Sub
    0.25
    pective
    0.24
     åķĨ
    0.24
    TB
    0.24
    abus
    0.24
     tj
    0.23
    çı¥
    0.23
    éĽī
    0.23
    Activations Density 0.003%

    No Known Activations