© 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. 40541
    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
    package
    -0.26
    åĪ©
    -0.26
    _bundle
    -0.25
    产ä¸ļåĮĸ
    -0.24
    contributors
    -0.24
    _deep
    -0.24
    ëīł
    -0.24
    ritt
    -0.24
    åĮħ
    -0.24
    é¡¿æŶ
    -0.23
    POSITIVE LOGITS
     TICK
    0.28
    otron
    0.27
    æĪĸå¤ļ
    0.27
    æĮĤ
    0.27
     hang
    0.26
     tick
    0.26
    )("
    0.25
    sb
    0.25
    SYM
    0.25
     letter
    0.24
    Activations Density 6.083%

    No Known Activations

    This feature has no known activations.