© 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. 3536
    Prev
    Next
    INDEX
    Explanations

    attribute access

    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
    ðŁĵIJ
    -0.29
    âĹĤ
    -0.28
    嬿
    -0.25
    âļĹ
    -0.24
    /Private
    -0.23
    ').'
    -0.23
    NSAttributedString
    -0.23
    é¹£
    -0.22
    anmar
    -0.22
    :'.$
    -0.22
    POSITIVE LOGITS
     getattr
    0.35
    ä»ĸçļĦ
    0.25
     @{$
    0.24
    æĤ£èĢħçļĦ
    0.24
    åŃ©åŃIJçļĦ
    0.24
    ä»ĸ们çļĦ
    0.24
     &(
    0.23
    åľ¨åħ¶
    0.22
    客æĪ·çļĦ
    0.22
    getattr
    0.21
    Activations Density 0.228%

    No Known Activations