© 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. 88632
    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
    ites
    -0.35
    ite
    -0.31
    hammer
    -0.28
    ITE
    -0.27
     hitch
    -0.26
    æ¯ķç«Ł
    -0.25
    æĿ·
    -0.24
     ``
    -0.24
    ITES
    -0.24
    ighting
    -0.24
    POSITIVE LOGITS
    èĥĦ
    0.26
    ssé
    0.25
    -spe
    0.25
    spe
    0.24
    urr
    0.23
     Urg
    0.23
    -mounted
    0.23
    curity
    0.23
    çĮ·
    0.23
    adows
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.