© 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. 3620
    Prev
    Next
    INDEX
    Explanations

    programming questions

    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
    .FindGameObjectWithTag
    -0.21
    )((((
    -0.20
     magna
    -0.19
    æĺ¯éĿŀ
    -0.19
     springfox
    -0.19
    ä½ľä¸ļ
    -0.19
    /stdc
    -0.19
    arehouse
    -0.19
     seedu
    -0.18
    ìį¨
    -0.18
    POSITIVE LOGITS
    BOSE
    0.23
    .Gray
    0.21
    npos
    0.21
    oftware
    0.20
     Qualität
    0.20
    .setToolTip
    0.20
    AYS
    0.20
    ',//
    0.19
    .bel
    0.19
    å«ĸ
    0.19
    Activations Density 0.001%

    No Known Activations