© 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. 827
    Prev
    Next
    INDEX
    Explanations

    S

    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
     pit
    -0.21
    /***************************************************************************↵
    -0.20
    r
    -0.20
     basically
    -0.20
    ins
    -0.20
    2
    -0.19
     compat
    -0.19
    aus
    -0.19
    à¸Ľà¸£à¸°à¸ª
    -0.19
    f
    -0.19
    POSITIVE LOGITS
    âļĹ
    0.30
     fkk
    0.30
    ','');↵
    0.30
    intégr
    0.29
    OffsetTable
    0.28
    InputBorder
    0.27
     )↵↵↵↵↵↵↵↵
    0.26
    åľ¨ä¼łå¥ĩ
    0.26
     newcom
    0.26
    clide
    0.26
    Activations Density 0.011%

    No Known Activations