© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    law

    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
    æĵį
    -0.24
    SystemService
    -0.22
     runApp
    -0.20
     Lane
    -0.19
    ï¼ģï¼ģ↵↵
    -0.19
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.19
    []=$
    -0.18
    BUF
    -0.18
     companyName
    -0.18
    Ĵ
    -0.17
    POSITIVE LOGITS
    ropri
    0.23
    -Methods
    0.23
    regor
    0.22
    tré
    0.21
    EEDED
    0.21
     GANG
    0.21
     volunte
    0.21
    âīª
    0.20
    iband
    0.20
    paralleled
    0.20
    Activations Density 0.013%

    No Known Activations