© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 685
    Prev
    Next
    INDEX
    Explanations

    What

    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
    Ũ
    -0.26
    apgolly
    -0.24
    '&&
    -0.24
    âĢ¦↵↵↵↵
    -0.24
     .↵↵↵↵
    -0.23
    âĵĩ
    -0.23
    ,,,,,,,,
    -0.23
    nqu
    -0.23
    çݩ家æľĭåıĭ
    -0.23
     Ä°zmir
    -0.22
    POSITIVE LOGITS
    ç½ij绾ç§ijæĬĢ
    0.21
    äºĭä¸ļåıijå±ķ
    0.20
    éĩįè¦ģ举æݪ
    0.19
    æ¶Īè´¹éľĢæ±Ĥ
    0.19
    _safe
    0.18
     Smith
    0.18
     dword
    0.18
     Gallagher
    0.18
     ipAddress
    0.18
     Maher
    0.18
    Activations Density 0.114%

    No Known Activations