© 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. 38552
    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
     //#
    -0.29
     cupid
    -0.28
    watch
    -0.27
    .syntax
    -0.27
     sodom
    -0.27
     cuckold
    -0.26
     sublist
    -0.25
    ç¬ijè¯Ŀ
    -0.24
    _bindings
    -0.24
    promotion
    -0.23
    POSITIVE LOGITS
     yes
    0.29
     ve
    0.29
     exp
    0.28
     very
    0.27
    lassen
    0.27
     clear
    0.26
     separate
    0.26
     closed
    0.26
     tight
    0.25
     interpre
    0.25
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.