© 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. 385
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
    picable
    -0.28
    ijľ
    -0.27
    ðŁĵIJ
    -0.25
    аÑĢÑĮ
    -0.25
    ollapsed
    -0.24
    forgettable
    -0.24
    âļĹ
    -0.23
    foundland
    -0.22
    alore
    -0.21
    ÑĤели
    -0.21
    POSITIVE LOGITS
    Ø£ÙĪض
    0.33
    CLUDING
    0.32
    ceans
    0.30
    regon
    0.29
    vertime
    0.29
    ÑĪедÑĪ
    0.29
    ehler
    0.28
     desar
    0.27
    تسÙħ
    0.25
    ulton
    0.24
    Activations Density 11.319%

    No Known Activations