© 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. 129205
    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
    etary
    -0.24
    èĤ¤èī²
    -0.24
     pervasive
    -0.24
    edback
    -0.24
     /^(
    -0.23
    ãģłãģ£ãģ¦
    -0.23
     EGL
    -0.23
     opposing
    -0.22
    顽
    -0.22
    res
    -0.22
    POSITIVE LOGITS
     reli
    0.26
     resolutions
    0.24
    ç°ł
    0.24
    .inner
    0.23
    ä¸ĢçĻ¾
    0.23
    á»·
    0.23
     Nielsen
    0.23
     Dish
    0.23
     cil
    0.23
     Accord
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.