© 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. 1859
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.27
     èĩªåĬ¨çĶŁæĪIJ
    -0.26
    irlines
    -0.26
     erotische
    -0.24
     çĶŁåij½åij¨æľŁ
    -0.23
     }}>{
    -0.23
    -Trump
    -0.23
    __),
    -0.23
     ×Ķ×ķ×ĵ
    -0.23
    économ
    -0.22
    POSITIVE LOGITS
     than
    0.25
    -than
    0.21
    '
    0.21
    ä½Ĩä¸įéĻIJäºİ
    0.21
    åij¢
    0.20
    İĺìĿ´
    0.19
    than
    0.19
    G
    0.19
    ewart
    0.18
     wParam
    0.18
    Activations Density 1.233%

    No Known Activations