© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50097
    Prev
    Next
    INDEX
    Explanations

    maybe, perhaps, or maybe that

    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
     przecież
    -0.10
    ukum
    -0.08
    ç³»çļĦ
    -0.08
     ведÑĮ
    -0.08
    ðŁĺī
    -0.08
    æģ¨ä¸įå¾Ĺ
    -0.08
    å¹´éĿĴ
    -0.08
    вед
    -0.08
    å²Ĥä¸įæĺ¯
    -0.07
    èĮĥæĸĩç½ij
    -0.07
    POSITIVE LOGITS
    als
    0.07
     easier
    0.07
    éĩį温
    0.07
    ł
    0.06
    åĪĨç±»
    0.06
    ات
    0.06
    æĶ¾
    0.06
     simpler
    0.06
    åħ¶ä»ĸæĸ¹å¼ı
    0.06
    åħĪ
    0.06
    Activations Density 0.014%

    No Known Activations