© 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. 40485
    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
    æĪĸèĢħæĺ¯
    -0.28
    ç¼Ļ
    -0.27
     medicines
    -0.25
    ogui
    -0.25
     clientele
    -0.25
    ase
    -0.25
    æīĢéľĢè¦ģçļĦ
    -0.24
    æĪĸæĺ¯
    -0.24
     just
    -0.23
     proc
    -0.23
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.43
     further
    0.41
     Further
    0.37
    Further
    0.36
     weiter
    0.34
     Weiter
    0.34
    éĢ²ä¸ĢæŃ¥
    0.32
    éĤ´
    0.31
     weitere
    0.28
    ãģķãĤīãģ«
    0.26
    Activations Density 16.607%

    No Known Activations

    This feature has no known activations.