© 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. 97259
    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
     healthier
    -0.29
    çĭ¬
    -0.27
    åģ¥åº·
    -0.26
    -ind
    -0.26
    åĨ·
    -0.26
     regenerate
    -0.25
    èĸ®
    -0.25
     Sark
    -0.25
     individ
    -0.25
    IGN
    -0.25
    POSITIVE LOGITS
    ë¥ľ
    0.26
     bied
    0.25
    -gap
    0.25
    unce
    0.25
    éĹ´éļĻ
    0.23
    ãĤ¦ãĤ§
    0.23
    ivos
    0.23
     Consent
    0.23
    brates
    0.23
     luckily
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.