© 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. 45929
    Prev
    Next
    INDEX
    Explanations

    methods and approaches

    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
    ä»İèĢĮå½±åĵį
    -0.07
    -NLS
    -0.07
    åıįä¹ĭ
    -0.07
    ndon
    -0.07
    ä¸ĢæĦı
    -0.07
     hanyalah
    -0.07
    ç»ıèIJ¥é¡¹çĽ®
    -0.07
    .unbind
    -0.07
     likewise
    -0.07
    åģļä»»ä½ķ
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.11
    åħ·ä½ĵ
    0.07
    à¹Ģà¸Ľà¹ĩà¸Ļหลัà¸ģ
    0.07
    æĪĸèĢħåħ¶ä»ĸ
    0.07
    åħ·ä½ĵæĥħåĨµ
    0.07
    åħ·ä½ĵæĿ¥è¯´
    0.07
    ä½Ĩæĺ¯çĶ±äºİ
    0.07
    åį³çĶ¨
    0.06
    etos
    0.06
    以ä¸ĭæĸ¹å¼ı
    0.06
    Activations Density 0.497%

    No Known Activations