© 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. 9519
    Prev
    Next
    INDEX
    Explanations

    exaggerated or absurd descriptions

    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
     vi
    -0.07
    çĶ»ç¬Ķ
    -0.07
     Akt
    -0.07
    æŁĶåĴĮ
    -0.07
    çģµæ´»
    -0.07
    欣èµı
    -0.06
     exhilar
    -0.06
    åij¼åķ¸
    -0.06
    åĸľ
    -0.06
    奴婢
    -0.06
    POSITIVE LOGITS
     exager
    0.09
    å¤¸å¼ł
    0.09
     exaggerated
    0.08
    èªĩå¼µ
    0.08
    _hyper
    0.08
    å§Ķåĵ¡éķ·
    0.08
    Ñģме
    0.08
    æĪij们æĬĬ
    0.07
     absurd
    0.07
    æĵ¬
    0.07
    Activations Density 0.442%

    No Known Activations