© 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. 40664
    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
    ches
    -0.28
    iture
    -0.27
    itures
    -0.27
    rete
    -0.26
    except
    -0.25
    娣
    -0.24
    .degree
    -0.24
    kee
    -0.24
    atures
    -0.24
     chắn
    -0.24
    POSITIVE LOGITS
    è¾IJ
    0.29
     Radi
    0.27
    -radius
    0.26
    鼷æĸ¯
    0.25
     fy
    0.24
     yaÅŁ
    0.24
     ([]
    0.23
    éľĸ
    0.23
    æĺŃ
    0.23
    ÑĦиз
    0.23
    Activations Density 0.243%

    No Known Activations

    This feature has no known activations.