© 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. 35-TRANSCODER-HP
    7. 40590
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    anj
    -0.29
     Finally
    -0.28
    ç»Ī
    -0.27
    _stdio
    -0.26
     finally
    -0.26
    (assign
    -0.26
    ι
    -0.26
    Finally
    -0.25
     Assign
    -0.25
    éĩĮ
    -0.25
    POSITIVE LOGITS
    iez
    0.28
     pies
    0.27
     losses
    0.26
    pies
    0.25
    äºıæįŁ
    0.25
     hairs
    0.24
     جدا
    0.24
    éģĵ士
    0.24
    é»ijæļĹ
    0.24
    æįĤ
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.