© 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. 2872
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    :'.$
    -0.30
    eldom
    -0.25
    */,↵
    -0.22
    abay
    -0.22
    marshall
    -0.22
    |=↵
    -0.21
    dux
    -0.21
    icensed
    -0.21
    .'.$
    -0.21
    zug
    -0.20
    POSITIVE LOGITS
    çłĶåĪ¶
    0.23
    æĹ¶ä»£ä¸ŃåĽ½
    0.21
    ç½ijé¦ĸ页
    0.21
    æĶ¿åºľéĩĩè´Ń
    0.20
     Multip
    0.19
    éļIJ身
    0.19
    éĩĩè´Ń
    0.19
    Calibri
    0.19
     cornerback
    0.19
    Serial
    0.19
    Activations Density 0.323%

    No Known Activations