© 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. 110923
    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
    ç¥Ł
    -0.27
    uby
    -0.26
     worries
    -0.25
     Uph
    -0.25
     nods
    -0.24
    obuf
    -0.24
     concerns
    -0.24
    @register
    -0.24
    uno
    -0.24
    éĹ¾
    -0.24
    POSITIVE LOGITS
    éŀĺ
    0.29
    roup
    0.28
    ãĤ·ãĤ¢
    0.25
     Gaw
    0.25
    ighet
    0.24
    ddit
    0.24
    annes
    0.24
    æ¡£
    0.23
    ADVERTISEMENT
    0.23
    ential
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.