© 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. 33-TRANSCODER-HP
    7. 54841
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¹ĸåĮº
    -0.30
    mtree
    -0.29
    ugs
    -0.28
    dig
    -0.28
     meio
    -0.26
    èĢģ乡
    -0.26
     rehab
    -0.26
     dig
    -0.25
    èŃ°
    -0.25
     UClass
    -0.25
    POSITIVE LOGITS
    -flex
    0.29
    çļ®
    0.27
    交
    0.27
     ske
    0.27
    ç¼ĺ
    0.26
    ä¿Ŀ
    0.26
    avit
    0.26
    (iter
    0.26
    aph
    0.25
    IFI
    0.25
    Activations Density 0.012%

    No Known Activations