© 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. 111298
    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
    æĸ°å»º
    -0.25
    æ¯į
    -0.25
    reate
    -0.25
    ç«Ļ
    -0.25
    åĢª
    -0.25
    è¶Ł
    -0.24
    繪
    -0.24
    强åĮĸ
    -0.23
    çĽijçIJĨ
    -0.23
    [size
    -0.23
    POSITIVE LOGITS
    ivalent
    0.26
    åħµåĻ¨
    0.25
    们éĥ½
    0.25
    Had
    0.24
    åľ¨åħ¨çIJĥ
    0.24
    guns
    0.24
    çĪ¸
    0.23
    iei
    0.23
    ereum
    0.23
    <g
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.