© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97366
    Prev
    Next
    INDEX
    Explanations

    research and institutions

    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
    å¾Īç®Ģåįķ
    -0.28
     sufficiently
    -0.27
    æ¯Ķè¾ĥç®Ģåįķ
    -0.26
     Burl
    -0.25
    ÑĢаÑĤ
    -0.25
     thieves
    -0.24
     Ideas
    -0.24
    »¿
    -0.23
     suff
    -0.23
    (['/
    -0.23
    POSITIVE LOGITS
     tá»ĭch
    0.26
    å®īå®ģ
    0.26
    osas
    0.24
    对ä»ĸ们
    0.24
    åħļåĴĮåĽ½å®¶
    0.24
     hm
    0.23
    ä¸İåħ¶
    0.23
    æķıæį·
    0.23
    Appending
    0.23
    ushman
    0.23
    Activations Density 0.023%

    No Known Activations