© 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. 185
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
     Decompiled
    -0.25
    ognito
    -0.24
     Após
    -0.21
    braska
    -0.20
     avalia
    -0.20
     lehet
    -0.19
    ispers
    -0.19
    #######↵
    -0.19
     setSupportActionBar
    -0.19
    owering
    -0.19
    POSITIVE LOGITS
    ðŁĵIJ
    0.27
    âļĹ
    0.25
    æĹ®
    0.21
    /↵↵↵↵
    0.20
    #ga
    0.20
    unik
    0.20
    岬
    0.20
    lius
    0.20
    íķĢ
    0.20
    )./
    0.19
    Activations Density 0.005%

    No Known Activations