© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 67
    Prev
    Next
    INDEX
    Explanations

    code and industry

    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
    oriously
    -0.25
    -Jul
    -0.23
    ].'
    -0.22
    resultSet
    -0.21
    bracht
    -0.20
    çݩ家æĿ¥è¯´
    -0.20
    AuthGuard
    -0.20
    ElementsBy
    -0.20
     TimeInterval
    -0.20
    ’B
    -0.20
    POSITIVE LOGITS
     there
    0.29
     only
    0.25
     entire
    0.24
    ä¸ĢåĪĩéĥ½
    0.23
    there
    0.22
    æķ´ä¸ª
    0.22
     whole
    0.21
    ç»
    0.21
     it
    0.21
     burden
    0.21
    Activations Density 1.851%

    No Known Activations