© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39663
    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
    Not in Any Lists

    No Comments

    Negative Logits
    rets
    -0.29
    form
    -0.28
     retard
    -0.26
    li
    -0.26
    ISC
    -0.25
     Roh
    -0.25
    icho
    -0.25
    esh
    -0.24
    ret
    -0.24
    审åĪ¤
    -0.24
    POSITIVE LOGITS
     bipartisan
    0.27
    ãģĦãģ£ãģ±ãģĦ
    0.27
    DataExchange
    0.26
    andise
    0.26
    人次
    0.26
     synonymous
    0.24
    å®ŀå®ŀåľ¨åľ¨
    0.24
     Veter
    0.23
    æİ¥
    0.23
    æĭ³
    0.23
    Activations Density 1.649%

    No Known Activations

    This feature has no known activations.