© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57784
    Prev
    Next
    INDEX
    Explanations

    be

    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
     accept
    -0.28
     pe
    -0.28
    æİ¥åıĹ
    -0.28
    å¸ĮæľĽèĩªå·±
    -0.27
     aff
    -0.27
     opin
    -0.27
     wish
    -0.27
     Accept
    -0.26
     per
    -0.26
    åı¯ä»¥èİ·å¾Ĺ
    -0.26
    POSITIVE LOGITS
    eways
    0.27
    oz
    0.26
    模èĮĥ
    0.25
    åľ¨é¦Ļ港
    0.25
    çħ§é¡§
    0.24
    classification
    0.24
    classify
    0.24
    鸷
    0.24
    åİŁèijĹ
    0.24
    owi
    0.24
    Activations Density 0.002%

    No Known Activations