© 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. 132
    Prev
    Next
    INDEX
    Explanations

    say digits

    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
    usercontent
    -0.21
    å·¥å§Ķ
    -0.21
     ØŃسÙĬÙĨ
    -0.20
    arhus
    -0.19
    èµİåĽŀ
    -0.19
    çĸ³
    -0.19
    è®®
    -0.19
    _IV
    -0.18
    æ¹İ
    -0.18
     queryset
    -0.18
    POSITIVE LOGITS
     difÃŃc
    0.27
    Reuters
    0.25
     Reuters
    0.25
    eteria
    0.21
    Else
    0.19
    utors
    0.19
     EVER
    0.19
    >>)
    0.19
    å°ıç¼ĸä¸Ģèµ·
    0.19
     stringWith
    0.19
    Activations Density 0.282%

    No Known Activations