© 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. 25-TRANSCODER-HP
    7. 109419
    Prev
    Next
    INDEX
    Explanations

    Code and licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     fancy
    -0.29
    еÑģÑĤво
    -0.26
    xit
    -0.26
    ä¸Ģ个人
    -0.24
    跨度
    -0.24
     differing
    -0.24
    åį§
    -0.24
    çļĦé¢ľèī²
    -0.24
    ä¸įäºĨ
    -0.24
    æĺ¯éĿŀ
    -0.23
    POSITIVE LOGITS
    owler
    0.27
    ç©·
    0.27
    toLocale
    0.25
     ways
    0.25
     Atl
    0.25
    OLA
    0.25
    碴
    0.25
    sense
    0.24
    审çIJĨ
    0.24
    lama
    0.24
    Activations Density 0.896%

    No Known Activations