© 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. 31-TRANSCODER-HP
    7. 17747
    Prev
    Next
    INDEX
    Explanations

    Code or technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¡£
    -0.28
     originals
    -0.25
    airy
    -0.25
    éta
    -0.24
    SetTitle
    -0.24
    führen
    -0.24
     conv
    -0.24
     Ballard
    -0.24
    丰
    -0.23
    è±IJ
    -0.23
    POSITIVE LOGITS
     terms
    0.25
    ites
    0.24
    egov
    0.24
    Dub
    0.23
    祸
    0.23
     AD
    0.23
     Car
    0.23
    pirit
    0.23
    à¸Ĺาà¸ĩ
    0.23
     Nicaragua
    0.23
    Activations Density 0.001%

    No Known Activations