© 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. 88763
    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
    Negative Logits
    ahl
    -0.31
    ord
    -0.29
    æŧ
    -0.28
     Me
    -0.25
     D
    -0.25
    âĢ¦the
    -0.25
    cul
    -0.24
     transit
    -0.24
     transport
    -0.23
    âĢ¦I
    -0.23
    POSITIVE LOGITS
    éĿŀ常å¤ļçļĦ
    0.32
    ç»ĻåĪ«äºº
    0.26
     ander
    0.26
    manifest
    0.25
    nable
    0.25
    æ·±æ·±åľ°
    0.25
    @if
    0.24
    æİĴæ¯Ĵ
    0.24
    dish
    0.24
    _nth
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.