© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1033
    Prev
    Next
    INDEX
    Explanations

    and

    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
    _rgba
    -0.21
    grupo
    -0.21
    åħ¶ä»ĸ
    -0.20
    polator
    -0.20
    以åıĬåħ¶ä»ĸ
    -0.20
    rippling
    -0.20
    -lfs
    -0.20
    ,readonly
    -0.19
    istinguished
    -0.19
    ç»ıéªĮåĴĮ
    -0.19
    POSITIVE LOGITS
    /or
    0.29
    rogen
    0.28
    -Owned
    0.27
    /*↵
    0.24
     fkk
    0.23
    DMETHOD
    0.23
    æŁ¥çľĭåħ¨æĸĩ
    0.23
    quot
    0.22
    :";č↵
    0.22
    âĴ¸
    0.21
    Activations Density 2.140%

    No Known Activations