© 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. 87127
    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
     reflexivity
    -0.27
     fö
    -0.27
    olds
    -0.25
    intl
    -0.25
     UIL
    -0.25
    åĿļ硬
    -0.25
     #__
    -0.24
    /target
    -0.24
     bubble
    -0.24
    bdd
    -0.23
    POSITIVE LOGITS
    lá
    0.29
    缸ç»ĵåIJĪ
    0.27
    çľĭä¸įåĩº
    0.25
    ych
    0.25
    YM
    0.24
    ä¸įå½±åĵį
    0.24
    look
    0.24
    ìľ¨
    0.24
    ÅĤam
    0.24
    -law
    0.24
    Activations Density 2.847%

    No Known Activations

    This feature has no known activations.