© 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. 50655
    Prev
    Next
    INDEX
    Explanations

    items, equipment, medical conditions

    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
    ahn
    -0.08
     crossed
    -0.08
    æ¯ĶæĻ®éĢļ
    -0.07
    agh
    -0.06
    åĪ°åºķæĺ¯
    -0.06
    æĥħæĦı
    -0.06
    æ¯Ķåħ¶ä»ĸ
    -0.06
    ä¸įä»ħæĺ¯
    -0.06
    -cross
    -0.06
    åijµ
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.16
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.12
     вÑĢоде
    0.11
     including
    0.10
    åĮħæĭ¬
    0.10
    æ¯Ķå¦Ĥ
    0.10
    èѬå¦Ĥ
    0.09
     kuten
    0.09
    including
    0.09
    å¦Ĥæ½®
    0.09
    Activations Density 0.295%

    No Known Activations