© 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. 56658
    Prev
    Next
    INDEX
    Explanations

    oil

    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
    enos
    -0.26
    éĩĮæĸ¯
    -0.25
     cess
    -0.24
    Slim
    -0.23
    ило
    -0.23
     sno
    -0.23
    Vtbl
    -0.23
    otto
    -0.23
    çļĦç§ĺå¯Ĩ
    -0.23
     Gutenberg
    -0.23
    POSITIVE LOGITS
    è´¯éĢļ
    0.29
    IRT
    0.25
    inton
    0.25
    wards
    0.24
     Miss
    0.24
     Ant
    0.24
     satur
    0.23
    anmar
    0.23
    ting
    0.23
     TimeUnit
    0.23
    Activations Density 0.012%

    No Known Activations