© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56871
    Prev
    Next
    INDEX
    Explanations

    appealing way to protect

    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
    angani
    -0.08
    رÙĬب
    -0.08
    ç»ħ
    -0.07
    obao
    -0.07
    ä¸īå®Ŀ
    -0.07
     Maggi
    -0.07
    /dat
    -0.07
    pig
    -0.07
    onces
    -0.07
    夺
    -0.07
    POSITIVE LOGITS
    ÂŃ
    0.07
    æĥ¨åı«
    0.06
     ÂŃ
    0.06
    ilin
    0.06
    rah
    0.06
    ra
    0.06
    omo
    0.06
    ah
    0.06
    Ra
    0.06
    aeda
    0.06
    Activations Density 0.386%

    No Known Activations