© 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. 40468
    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
    ä»»
    -0.31
    åIJĦèĩª
    -0.28
    éĺ¶çº§
    -0.27
    轨éģĵ
    -0.27
    emit
    -0.27
    argument
    -0.26
    éĩįè¦ģä½ľçĶ¨
    -0.26
    æĢĿç´¢
    -0.26
    æ¤ħåŃIJ
    -0.26
    驶
    -0.26
    POSITIVE LOGITS
    пан
    0.28
    STALL
    0.26
     говоÑĢиÑĤ
    0.25
     day
    0.25
    pf
    0.25
     found
    0.25
    IED
    0.25
     continues
    0.25
     SCT
    0.24
     наÑĢ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.