© 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. 97377
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Anc
    -0.34
     Spin
    -0.30
    æ¥ŀ
    -0.28
    ä¾ĭåŃIJ
    -0.28
    Spin
    -0.27
    è¾ħ
    -0.26
     spin
    -0.25
    ãģ¾ãģ¾
    -0.25
     ourselves
    -0.25
    pent
    -0.24
    POSITIVE LOGITS
    ä¸īæľŁ
    0.26
    eros
    0.23
    OPS
    0.23
    lops
    0.23
    %"↵
    0.23
    iod
    0.23
    плод
    0.23
    aps
    0.23
    opl
    0.23
     membership
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.