© 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. 38537
    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
    ppy
    -0.29
     jc
    -0.29
    -scrollbar
    -0.26
    ãĥ«ãĥī
    -0.26
    iddles
    -0.26
     puss
    -0.25
    ãĥ¼ãĤº
    -0.25
    ogr
    -0.25
    irá
    -0.25
    éis
    -0.25
    POSITIVE LOGITS
    æķ°åĢ¼
    0.29
    èĿĻ
    0.27
     '
    0.26
    int
    0.26
     current
    0.24
    å¾Īå¼Ģå¿ĥ
    0.24
     part
    0.24
    L
    0.24
    å®ļçĤ¹
    0.24
     predecessor
    0.23
    Activations Density 6.418%

    No Known Activations

    This feature has no known activations.