© 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. 467
    Prev
    Next
    INDEX
    Explanations

    database id fields

    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
     lineback
    -0.30
    åºĶæĶ¶è´¦
    -0.30
     prostit
    -0.27
    stdexcept
    -0.25
     fflush
    -0.25
    ä½ıæĪ¿åħ¬ç§¯
    -0.25
     OnCollision
    -0.24
    cstdint
    -0.23
     Tradable
    -0.23
    å¼Ģå¥ĸç»ĵæŀľ
    -0.23
    POSITIVE LOGITS
    -await
    0.38
     beneficiation
    0.29
    ,DB
    0.29
    -UA
    0.29
    :'.$
    0.28
    ".↵↵↵↵
    0.28
    -Compatible
    0.28
     practition
    0.27
    _AST
    0.26
    å§ĭ建
    0.26
    Activations Density 4.265%

    No Known Activations