© 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. 38784
    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
     angel
    -0.25
     chests
    -0.24
     jes
    -0.24
    å²Ļ
    -0.24
    çIJĨ解åĴĮ
    -0.23
     whirl
    -0.23
     shovel
    -0.23
    lobber
    -0.22
    éĵ§
    -0.22
    æŃ»è§Ĵ
    -0.22
    POSITIVE LOGITS
    pose
    0.27
    aring
    0.25
    aly
    0.24
    poses
    0.24
    nings
    0.23
    cÃŃ
    0.23
    åĭĩ
    0.23
    æĺ¯ä¸Ģç§į
    0.23
    GW
    0.22
    åĨµä¸Ķ
    0.22
    Activations Density 1.609%

    No Known Activations

    This feature has no known activations.