© 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. 38814
    Prev
    Next
    INDEX
    Explanations

    Code/system files

    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
     aqu
    -0.29
     annual
    -0.28
     always
    -0.27
    opic
    -0.26
     brick
    -0.25
     ALWAYS
    -0.25
    agenta
    -0.25
     Aqu
    -0.25
     fetish
    -0.25
    afen
    -0.25
    POSITIVE LOGITS
    å½¢å¼ı
    0.40
    lore
    0.29
    çļĦå½¢å¼ı
    0.27
    æĢį
    0.26
     form
    0.26
     íĺķíĥľ
    0.25
    ä¹ĺåĿIJ
    0.25
    示æĦı
    0.24
    ŀ
    0.24
     "','
    0.24
    Activations Density 0.423%

    No Known Activations