© 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. 40576
    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
    l
    -0.33
    later
    -0.32
    lab
    -0.31
     tù
    -0.28
    lam
    -0.27
    tfoot
    -0.27
    lanması
    -0.27
    late
    -0.27
     referenced
    -0.26
    lat
    -0.26
    POSITIVE LOGITS
    ä¼ij
    0.26
    æ·Ŀ
    0.26
    enheim
    0.25
    berg
    0.25
    ABI
    0.25
    anio
    0.25
    VID
    0.24
    icas
    0.24
    ("?
    0.24
    aim
    0.24
    Activations Density 53.737%

    No Known Activations

    This feature has no known activations.