© 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. 1721
    Prev
    Next
    INDEX
    Explanations

    analyze/determine

    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
    åİĨåı²æĸ°
    -0.27
    .isBlank
    -0.23
    quential
    -0.22
    SharedPointer
    -0.21
    ëħģ
    -0.21
    <small
    -0.21
    *Math
    -0.21
    prar
    -0.20
    ãĤĴåĪ©çĶ¨ãģĻãĤĭ
    -0.20
    .Euler
    -0.20
    POSITIVE LOGITS
    åĪĨæŀIJ
    0.35
    æī¾åĩº
    0.34
     determine
    0.33
     analysis
    0.31
     determining
    0.30
     comparison
    0.30
     determines
    0.29
    äºĨ解
    0.29
    æ¯Ķè¾ĥ
    0.29
     examine
    0.28
    Activations Density 5.538%

    No Known Activations