© 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. 38834
    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
    ported
    -0.27
    渴
    -0.27
     Maz
    -0.27
    ilinear
    -0.26
    itional
    -0.25
    Forms
    -0.25
    uant
    -0.25
    ball
    -0.25
    å£ģ
    -0.24
    éĿ©åij½
    -0.24
    POSITIVE LOGITS
    /pg
    0.28
    /install
    0.26
    /top
    0.25
     hôm
    0.25
    å°ıç¼ĸ
    0.24
    å¸ĸ
    0.24
    /license
    0.24
     isConnected
    0.24
     ten
    0.24
    density
    0.23
    Activations Density 0.038%

    No Known Activations

    This feature has no known activations.