© 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. 38672
    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
    ãĢĬ
    -0.26
    辩
    -0.26
    辨
    -0.24
    ä¸Ŀ绸
    -0.24
     adequ
    -0.24
     Malik
    -0.24
     Savings
    -0.23
    :S
    -0.23
     Cycling
    -0.23
    æľīéĹ®é¢ĺ
    -0.23
    POSITIVE LOGITS
     zwar
    0.25
    ä»ĩæģ¨
    0.24
    aste
    0.24
    èĽİ
    0.24
     faut
    0.23
     grav
    0.22
     des
    0.22
    åªĴ
    0.22
    è¡Ģ液
    0.22
    çĸĥ
    0.22
    Activations Density 0.230%

    No Known Activations

    This feature has no known activations.