© 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. 113028
    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
    Negative Logits
     gist
    -0.29
    ä¸Ģç¢Ĺ
    -0.28
    `${
    -0.27
    éĢļçĶ¨
    -0.26
    copies
    -0.25
     sil
    -0.25
    bens
    -0.25
     michael
    -0.25
    åı£æ°´
    -0.24
     inequalities
    -0.23
    POSITIVE LOGITS
    izador
    0.28
    ÑĮÑİ
    0.26
    )--
    0.24
    olucion
    0.24
    /display
    0.24
    Term
    0.24
    ption
    0.23
    aul
    0.23
    Uploaded
    0.23
    psy
    0.23
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.