© 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. 56693
    Prev
    Next
    INDEX
    Explanations

    coding and technical documentation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Talent
    -0.29
    èŁĴ
    -0.28
    Persistence
    -0.26
    imid
    -0.26
     persistent
    -0.26
    persistent
    -0.25
    meld
    -0.25
    ignite
    -0.24
    vince
    -0.24
     Persistent
    -0.24
    POSITIVE LOGITS
    ä¸ĢåĽŀäºĭ
    0.28
    ilog
    0.27
     fiscal
    0.27
    æijĩ头
    0.27
    ascus
    0.26
    op
    0.25
    .setVertical
    0.24
     FY
    0.24
     Uncomment
    0.24
    åĽ°æĥij
    0.24
    Activations Density 0.001%

    No Known Activations