© 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. 111322
    Prev
    Next
    INDEX
    Explanations

    H

    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
    awks
    -0.29
     ëĭ¹ìĭľ
    -0.28
     <![
    -0.25
     addObject
    -0.25
    åĬłæ²¹
    -0.25
    éĤ£ä¸ªæŶåĢĻ
    -0.24
    èĢħçļĦ
    -0.24
    æĸ°å¾ģç¨ĭ
    -0.24
    èĦļä¸ĭ
    -0.24
    ä¸įå¿ĺ
    -0.24
    POSITIVE LOGITS
     Flynn
    0.30
     Tu
    0.28
     reportedly
    0.27
     |
    0.27
     spreads
    0.27
    appe
    0.26
    cq
    0.26
    ãĥĩãĥ³
    0.26
    |x
    0.25
    æľ«
    0.25
    Activations Density 0.060%

    No Known Activations