© 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. 88666
    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
    åľ°å¸¦
    -0.29
    éĻ¨
    -0.25
     æĽ
    -0.24
    ouser
    -0.24
    -cur
    -0.24
    Ñīение
    -0.24
    çļĦ身影
    -0.23
     cámara
    -0.23
    -handle
    -0.23
    andle
    -0.23
    POSITIVE LOGITS
    æľµ
    0.27
    Visited
    0.26
    keiten
    0.25
    æĢĤ
    0.25
    unched
    0.24
    Progress
    0.24
    (ARG
    0.24
    JECT
    0.24
    (progress
    0.24
    (*(
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.