© 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. 22-TRANSCODER-HP
    7. 130142
    Prev
    Next
    INDEX
    Explanations

    Microns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kea
    -0.29
    unter
    -0.26
    case
    -0.26
    æĥħåĨµè¿Ľè¡Į
    -0.26
    æīģ
    -0.26
    bite
    -0.26
    finger
    -0.25
    ãĥ¯ãĥ¼
    -0.25
    é¼ĵ
    -0.25
    uggling
    -0.24
    POSITIVE LOGITS
    éĤ»
    0.26
    ultipart
    0.25
    .lastIndexOf
    0.24
    æī¾ä¸įåĪ°
    0.24
    x
    0.23
    _stdio
    0.23
    éħįç½®
    0.23
    毫æĹł
    0.23
    ARCH
    0.23
    Official
    0.23
    Activations Density 0.056%

    No Known Activations