© 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. 38625
    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
    èı½
    -0.27
     scenic
    -0.25
    è¦ģç´ł
    -0.23
    èĮ¸
    -0.23
    ees
    -0.23
    xfff
    -0.23
    åĩºåı°
    -0.23
    _elems
    -0.23
    otions
    -0.23
     furniture
    -0.23
    POSITIVE LOGITS
     Zug
    0.29
    âĬĩ
    0.27
    uma
    0.27
    머
    0.26
    éŃĤ
    0.26
    éŁ³
    0.26
    ource
    0.26
    tan
    0.25
     Omni
    0.25
    æºIJ
    0.25
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.