© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 326
    Prev
    Next
    INDEX
    Explanations

    local

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Premiership
    -0.39
     Playoff
    -0.35
     winger
    -0.34
     midfielder
    -0.33
     endors
    -0.33
     occas
    -0.33
    åĽ½éĻħåIJĪä½ľ
    -0.29
    åľ¨åĽ½å¤ĸ
    -0.29
     Erectile
    -0.29
     algu
    -0.29
    POSITIVE LOGITS
     local
    0.35
    ,{"
    0.34
    æľ¬åľ°
    0.32
     locally
    0.32
     Local
    0.29
    local
    0.28
    "<?
    0.28
     ohio
    0.28
     locals
    0.28
     libertin
    0.28
    Activations Density 9.031%

    No Known Activations