© 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. 350
    Prev
    Next
    INDEX
    Explanations

    referencing citations 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
    omite
    -0.21
    leanor
    -0.21
    ocaly
    -0.21
    beits
    -0.21
    serter
    -0.20
     BCH
    -0.20
    enment
    -0.20
    åħ¨èµĦåŃIJ
    -0.20
    arranty
    -0.20
    voke
    -0.20
    POSITIVE LOGITS
    æ¥ŀ
    0.21
     kako
    0.21
    fühl
    0.20
    åģ²
    0.20
    ä¼ĹæīĢåij¨
    0.19
     mädchen
    0.19
     tako
    0.19
     ula
    0.19
    stateParams
    0.19
    CPP
    0.18
    Activations Density 0.164%

    No Known Activations