© 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. 52785
    Prev
    Next
    INDEX
    Explanations

    academic 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
    ardown
    -0.26
    ä¼°åĢ¼
    -0.26
    çĶĦ
    -0.25
    .Companion
    -0.24
    à¸łà¸²à¸Ħ
    -0.24
    æľªæĪIJå¹´
    -0.23
    à¸ł
    -0.23
    leaf
    -0.23
    éĩį建
    -0.23
    Estimated
    -0.23
    POSITIVE LOGITS
     sup
    0.35
     pan
    0.34
     dét
    0.28
     pans
    0.28
     trans
    0.27
     dispute
    0.25
     regul
    0.25
     tá»ij
    0.25
     hypert
    0.25
     pap
    0.25
    Activations Density 0.028%

    No Known Activations