© 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. 38611
    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
    bian
    -0.27
    åİŁæłĩé¢ĺ
    -0.27
    xec
    -0.27
    maker
    -0.26
    aida
    -0.26
    abb
    -0.25
    arters
    -0.25
    ix
    -0.25
    UPI
    -0.25
    .pivot
    -0.25
    POSITIVE LOGITS
    arez
    0.27
    åı£è¢ĭ
    0.26
     cubic
    0.26
    _listener
    0.26
    容éĩı
    0.25
    è´¨éĩıåĴĮ
    0.25
    骢
    0.24
    éĸī
    0.24
    æĥ¹
    0.24
     Decoration
    0.24
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.