© 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. 40794
    Prev
    Next
    INDEX
    Explanations

    News and public service announcements

    np_max-act-logits · gemini-2.0-flash
    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
    åĪ¶ä½ľ
    -0.34
    æķĻèĤ²
    -0.32
    æĶ¹éĿ©
    -0.31
    èµĦæºIJ
    -0.31
     contention
    -0.28
     chemistry
    -0.28
    çĶŁäº§åĴĮ
    -0.28
    解
    -0.28
     resource
    -0.28
    çĶŁäº§
    -0.28
    POSITIVE LOGITS
     Newspaper
    0.33
     Municip
    0.30
     Basketball
    0.29
     Rescue
    0.28
     Municipal
    0.28
     Mandatory
    0.27
     Libertarian
    0.27
     B
    0.27
     Newsletter
    0.27
     Newsp
    0.27
    Activations Density 0.701%

    No Known Activations