© 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. 479
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
     ï¼Ī
    -0.46
     (
    -0.43
    ï¼Ī
    -0.36
     (↵
    -0.35
     (č↵
    -0.30
    ãĢĤï¼Ī
    -0.29
     (↵↵
    -0.27
     (“
    -0.27
    !).↵↵
    -0.26
     (!
    -0.26
    POSITIVE LOGITS
    )
    0.40
    ä¸ĭ称
    0.30
    ),
    0.29
    ornment
    0.27
     fkk
    0.26
    )ï¼Į
    0.26
    ãĢķ
    0.25
     jihadists
    0.24
    chestra
    0.24
     Erectile
    0.24
    Activations Density 4.332%

    No Known Activations