© 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. 64421
    Prev
    Next
    INDEX
    Explanations

    responsible for actions 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
    ยม
    -0.07
    æĿijæĿij
    -0.07
    çĪ¶å¥³
    -0.06
    æĥ£
    -0.06
    äºī夺
    -0.06
    _extract
    -0.06
    ợi
    -0.06
     rahas
    -0.06
     ancam
    -0.06
    å¿ĥåľ°
    -0.06
    POSITIVE LOGITS
    åIJİç»Ń
    0.09
    å¦Ĥåħ¶
    0.08
     failures
    0.08
    æĹ¥åIJİ
    0.08
     attributed
    0.08
    ä¹ĭåIJİçļĦ
    0.08
    å½Ĵå±ŀäºİ
    0.08
    åIJİæĿ¥çļĦ
    0.08
    溢
    0.08
    éĢłæĪIJçļĦæįŁå¤±
    0.08
    Activations Density 0.238%

    No Known Activations