© 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. 418
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
     Playoff
    -0.36
    buat
    -0.28
    .RadioButton
    -0.28
    structuring
    -0.23
     grues
    -0.23
    '>".$
    -0.23
    ().'/
    -0.23
     ula
    -0.23
    thinkable
    -0.23
    /AFP
    -0.23
    POSITIVE LOGITS
    åĵĤ
    0.24
    æ´Į
    0.23
     PointF
    0.23
     Svg
    0.23
    PIO
    0.23
    æį¢åı¥è¯Ŀ
    0.22
     Erectile
    0.22
     TextAlign
    0.21
     LinearGradient
    0.20
    buquerque
    0.20
    Activations Density 2.036%

    No Known Activations