© 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. 27-TRANSCODER-HP
    7. 58424
    Prev
    Next
    INDEX
    Explanations

    business and technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħħ足
    -0.27
     statically
    -0.25
     Psychic
    -0.24
    ç¼ī
    -0.24
    å¥Ķ
    -0.24
     scrolling
    -0.24
    (problem
    -0.23
    alu
    -0.23
     üzer
    -0.23
    çļĦæĸĩåŃĹ
    -0.23
    POSITIVE LOGITS
    liest
    0.26
    ģ
    0.25
    ors
    0.25
    åĪ©çī©
    0.24
    è¯
    0.24
    ÑĤиÑĢ
    0.24
    æĭ¾
    0.24
    erable
    0.24
     nor
    0.23
     gag
    0.23
    Activations Density 0.002%

    No Known Activations