© 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. 1588
    Prev
    Next
    INDEX
    Explanations

    scientific and technical text

    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
     ++)↵
    -0.23
    åļħ
    -0.20
    âĪĿ
    -0.20
    æīĵåĮħ
    -0.20
    exit
    -0.19
    è¿ĩå¾Ĺ
    -0.18
    NAL
    -0.18
     sharedInstance
    -0.18
    æĤ¨çļĦåŃ©åŃIJ
    -0.18
    è¶Ĭæĺ¯
    -0.18
    POSITIVE LOGITS
    'order
    0.26
    ccoli
    0.25
    åĢį
    0.23
    ELLOW
    0.21
     curt
    0.21
    .isSuccessful
    0.21
     addCriterion
    0.20
    沨
    0.20
    ();++
    0.20
    combe
    0.20
    Activations Density 0.001%

    No Known Activations