© 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. 130899
    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
    adier
    -0.28
    iesz
    -0.26
     settled
    -0.24
    -slot
    -0.24
    æĻ¯å¾·
    -0.24
    è²´
    -0.24
    æĢ»çĽij
    -0.24
    depend
    -0.24
     Republic
    -0.23
     credited
    -0.23
    POSITIVE LOGITS
    /time
    0.24
    æ°´éĩı
    0.24
    æ·¹
    0.24
    æĦŁæĥħ
    0.23
    è¿Ļä¸ĢçĤ¹
    0.23
    cdc
    0.22
    reve
    0.22
     revealing
    0.22
    ico
    0.22
     colored
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.