© 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. 40775
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
    ï½ŀ↵↵
    -0.42
     ..."↵↵
    -0.41
    âĢ¦”↵↵
    -0.41
     #↵↵
    -0.40
     ”↵↵
    -0.38
     —↵↵
    -0.38
    (),↵↵
    -0.38
    ï¼Į↵↵
    -0.38
     /↵↵
    -0.38
     %↵↵
    -0.37
    POSITIVE LOGITS
    Mike
    0.32
    Tony
    0.30
     Mike
    0.30
    Chris
    0.29
    Juan
    0.28
     pizza
    0.28
    Harry
    0.28
    ?
    0.28
     Chris
    0.27
     trucks
    0.27
    Activations Density 0.987%

    No Known Activations