© 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. 38877
    Prev
    Next
    INDEX
    Explanations

    Recommended Citation

    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
    ↵
    -0.07
    apse
    -0.07
    cze
    -0.06
    ÙĪع
    -0.06
    erten
    -0.06
    åħ·ä½ĵåĨħ容
    -0.06
    åħ·ä½ĵæĥħåĨµ
    -0.06
    ç©¿æ¢Ń
    -0.06
    å·¥ä½ľæĬ¥åijĬ
    -0.06
    åĴĮèĥ½åĬĽ
    -0.06
    POSITIVE LOGITS
    plar
    0.08
    ĥĿ
    0.08
    igd
    0.08
    举åįİ
    0.08
     Kemb
    0.08
    adium
    0.07
    depend
    0.07
    ¾
    0.07
    ç²ī红
    0.07
    -placeholder
    0.07
    Activations Density 0.006%

    No Known Activations