© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9686
    Prev
    Next
    INDEX
    Explanations

    for the sake of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <|box_end|>
    -0.12
    sWith
    -0.10
    ลฯ
    -0.09
    ìľ¼ë¡ľ
    -0.08
    人士
    -0.08
    ernels
    -0.08
    aldas
    -0.08
    à¥į
    -0.08
    ìľ¼ë¡ľëĬĶ
    -0.07
    人士çļĦ
    -0.07
    POSITIVE LOGITS
    ÃŃso
    0.10
     اÛĮÙĨÚ©Ùĩ
    0.10
    chter
    0.09
     viá»ĩc
    0.09
    èµ·è§ģ
    0.09
    aging
    0.08
     Ñĩего
    0.08
    /from
    0.08
    à¸Ĺีà¹Īà¸Īะ
    0.08
    getting
    0.08
    Activations Density 0.001%

    No Known Activations