© 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. 129368
    Prev
    Next
    INDEX
    Explanations

    the

    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
     choice
    -0.27
     tand
    -0.25
    ingly
    -0.24
     safeguards
    -0.24
     rallies
    -0.24
    Öģ
    -0.23
    é¦ĸ家
    -0.23
    ew
    -0.23
    åľ°ä½į
    -0.23
    éļ¾æĢª
    -0.23
    POSITIVE LOGITS
    ORB
    0.30
    ãģĹãģĭ
    0.28
     Smithsonian
    0.25
    viso
    0.25
    éĥ½èĥ½
    0.24
    ĪæĿĥ
    0.24
    ãģıãĤĮ
    0.24
     affid
    0.24
    ÈĻi
    0.24
    åįļçī©
    0.23
    Activations Density 0.037%

    No Known Activations