© 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. 1601
    Prev
    Next
    INDEX
    Explanations

    like

    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
    âĺī
    -0.28
    byss
    -0.28
    berra
    -0.28
     ×Ķ×ķ×ĵ
    -0.28
    )new
    -0.28
    ?f
    -0.26
    'RE
    -0.26
    TextWriter
    -0.26
    ehler
    -0.26
    ncy
    -0.26
    POSITIVE LOGITS
    -like
    0.41
    -based
    0.39
    -type
    0.36
    like
    0.31
    -style
    0.30
    -shaped
    0.28
    ç±»
    0.28
    -Based
    0.28
    å¼ıçļĦ
    0.27
    ish
    0.27
    Activations Density 9.121%

    No Known Activations