© 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. 3572
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    offsetof
    -0.25
    家åĸ»
    -0.23
    :UITableView
    -0.22
     uda
    -0.22
     stringWithFormat
    -0.21
     Ksi
    -0.20
    ç¹Ħ
    -0.20
    æĹıèĩªæ²»
    -0.20
     ActionTypes
    -0.20
    åľ¨ä¼łå¥ĩ
    -0.20
    POSITIVE LOGITS
    ournaments
    0.24
    æ°¸ä¹ħ
    0.21
    çªĺ
    0.19
    écoute
    0.18
    ç§ijåѦæĬĢæľ¯
    0.18
    并ä¸İ
    0.18
     Coroutine
    0.18
    u
    0.18
    endencies
    0.17
    çģ°
    0.17
    Activations Density 0.001%

    No Known Activations