© 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. 38636
    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
    !
    -0.32
    å¾Ĺ
    -0.29
     till
    -0.28
    ô
    -0.28
    ae
    -0.28
    ula
    -0.28
    F
    -0.28
    è£ħç½®
    -0.27
    aven
    -0.27
     +
    -0.27
    POSITIVE LOGITS
     conspicuous
    0.28
    mast
    0.27
     invalidated
    0.27
    inality
    0.27
    callbacks
    0.26
     chall
    0.26
     defaulted
    0.26
     ssid
    0.26
     straw
    0.26
    walking
    0.26
    Activations Density 1.138%

    No Known Activations

    This feature has no known activations.