© 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. 55464
    Prev
    Next
    INDEX
    Explanations

    quality, score, or level

    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
    ovid
    -0.09
    ypical
    -0.07
    åĨĮ
    -0.07
    èĻ½çĦ¶æľī
    -0.07
    æģ°
    -0.07
    åĮħæĭ¬äºĨ
    -0.07
     Crime
    -0.07
     há»ķ
    -0.07
    iteli
    -0.07
     Including
    -0.06
    POSITIVE LOGITS
    è¶Ĭä½İ
    0.10
    è¶Ĭ
    0.10
    è¶Ĭæĺ¯
    0.09
    è¶Ĭå°ı
    0.08
    çļĦé«ĺä½İ
    0.08
    è¶Ĭé«ĺ
    0.08
    é«ĺä½İ
    0.08
    è¶Ĭå°ij
    0.08
     ยิà¹Īà¸ĩ
    0.08
     proxy
    0.08
    Activations Density 0.120%

    No Known Activations