© 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. 20-TRANSCODER-HP
    7. 64783
    Prev
    Next
    INDEX
    Explanations

    geography fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     im
    -0.26
    สรร
    -0.26
    imeType
    -0.26
     materia
    -0.25
    agra
    -0.24
    ä¿®
    -0.24
    è£ħåį¸
    -0.24
     rgba
    -0.24
    atters
    -0.23
    (entity
    -0.23
    POSITIVE LOGITS
    ĺ认
    0.29
    èĩ³æѤ
    0.28
    å¿ĥçIJĨåģ¥åº·
    0.26
    ittest
    0.26
     distr
    0.25
    elter
    0.25
    ä¸Ģå¤Ħ
    0.25
    ovel
    0.25
     Shield
    0.24
    antro
    0.24
    Activations Density 10.012%

    No Known Activations