© 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. 30-TRANSCODER-HP
    7. 96963
    Prev
    Next
    INDEX
    Explanations

    Locations and place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ģç«Ļå¼ı
    -0.26
    篡
    -0.26
    AGMA
    -0.25
    为æĤ¨
    -0.25
     Yankee
    -0.25
    quets
    -0.24
    -Mar
    -0.24
     Feather
    -0.24
    [offset
    -0.24
     REGISTER
    -0.23
    POSITIVE LOGITS
    lectual
    0.30
     scop
    0.28
    azine
    0.26
    jec
    0.25
    oire
    0.25
    è´Ŀå°Ķ
    0.25
    rike
    0.25
     MSR
    0.24
    gate
    0.24
    æľīèī²
    0.24
    Activations Density 0.887%

    No Known Activations