© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2592
    Prev
    Next
    INDEX
    Explanations

    Names and people

    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
    ,No
    -0.35
    ;br
    -0.33
    ]={↵
    -0.28
    :<?
    -0.27
    ,Th
    -0.27
    "path
    -0.26
    ;set
    -0.26
    /MPL
    -0.25
    ',//
    -0.25
    ¬ģ
    -0.24
    POSITIVE LOGITS
     OnTrigger
    0.31
     OnCollision
    0.21
     OnTriggerEnter
    0.21
    ç¥İ
    0.20
     spelled
    0.20
     maths
    0.20
    ins
    0.20
    èī¾æ»ĭ
    0.19
    (e
    0.19
    è¯Ļ
    0.19
    Activations Density 0.339%

    No Known Activations