© 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. 50454
    Prev
    Next
    INDEX
    Explanations

    cellulose breakdown

    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
    æĬĬ人
    -0.08
    绣ä¸Ģéĥ¨ç½²
    -0.08
    å·©
    -0.07
     rinn
    -0.07
    aimer
    -0.07
    æIJIJ
    -0.07
    ä¿Ĭ
    -0.07
     odb
    -0.07
     globally
    -0.07
     Renew
    -0.07
    POSITIVE LOGITS
     originally
    0.11
    åİŁæľ¬
    0.11
    åİŁæľ¬çļĦ
    0.11
    åİŁæľī
    0.10
    åİŁæĿ¥çļĦ
    0.10
    åİŁæľīçļĦ
    0.10
    åİŁæĿ¥
    0.09
    åİŁæľ¬æĺ¯
    0.09
    åİŁåħĪ
    0.09
    à¹Ģà¸Ķิม
    0.08
    Activations Density 0.009%

    No Known Activations