© 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. 40597
    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
    -east
    -0.28
    ä¸İä¼Ĺ
    -0.27
     suffice
    -0.26
    ä¹Łä¸įæķ¢
    -0.26
     eastern
    -0.26
    ç»Ĩ
    -0.25
     Honest
    -0.25
     Euras
    -0.25
    ä»İåݻ年
    -0.24
    ä¸ĢåŃĹ
    -0.24
    POSITIVE LOGITS
    loyd
    0.30
    ixel
    0.28
    riend
    0.28
    ibi
    0.27
    emme
    0.26
     breath
    0.26
    uess
    0.26
    iasi
    0.26
    bre
    0.26
    ission
    0.26
    Activations Density 0.018%

    No Known Activations