© 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. 1491
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    islation
    -0.21
    .AlertDialog
    -0.20
     clearColor
    -0.20
    irlines
    -0.20
    DDS
    -0.20
    æĢħ
    -0.20
    åIJł
    -0.20
     $$$
    -0.20
    KC
    -0.19
    æĺ¼å¤ľ
    -0.19
    POSITIVE LOGITS
    -strokes
    0.29
    alink
    0.28
    licted
    0.25
     még
    0.25
    aised
    0.25
    ogenerated
    0.24
    urrenc
    0.24
    mnop
    0.24
     POLITICO
    0.24
    ingleton
    0.24
    Activations Density 1.643%

    No Known Activations