© 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. 87027
    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
    opyright
    -0.28
    è´µ
    -0.26
     Samar
    -0.25
    ereo
    -0.25
    oco
    -0.24
    éĩ
    -0.24
     Augusta
    -0.23
    ENCE
    -0.23
    doi
    -0.23
    ToDate
    -0.23
    POSITIVE LOGITS
    .comp
    0.27
    第ä¸ī个
    0.26
    KI
    0.25
    Kir
    0.25
    æĿĤ
    0.25
    çĺª
    0.25
    aram
    0.24
    Where
    0.23
    änd
    0.23
    交ç»Ļ
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.