© 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. 17678
    Prev
    Next
    INDEX
    Explanations

    heterotrophic, autotrophic, feeding, carnivorous

    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
    ª
    -0.07
    ograf
    -0.07
    绽
    -0.07
    lixir
    -0.07
    åIJĮæŃ¥
    -0.07
     chÃŃ
    -0.06
    éĥģ
    -0.06
    åİĨ
    -0.06
    æŃ·
    -0.06
    éħ¥
    -0.06
    POSITIVE LOGITS
     relying
    0.09
     reliance
    0.09
    éĿłèĩªå·±
    0.09
    è¦ģéĿł
    0.08
     rely
    0.08
    éĿł
    0.08
    ä¾ĿéĿł
    0.08
    дÑĥк
    0.08
    æĸ¹å¼ıçļĦ
    0.08
     sources
    0.08
    Activations Density 0.039%

    No Known Activations