© 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. 11540
    Prev
    Next
    INDEX
    Explanations

    tropical regions and species

    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
     Isra
    -0.09
    åĨ¬å¥¥ä¼ļ
    -0.08
    æĪĪå£ģ
    -0.08
    çĻ½å±±
    -0.08
    奶çīĽ
    -0.08
    atron
    -0.08
     Bard
    -0.08
    çī§ç¾Ĭ
    -0.07
    çĻ½ç¾Ĭ
    -0.07
    åĨ¬å¥¥
    -0.07
    POSITIVE LOGITS
    çĥŃ带
    0.14
    ropical
    0.14
     tropical
    0.14
     Tropical
    0.13
    ungle
    0.13
     jungle
    0.12
    鼨æŀĹ
    0.12
     Coconut
    0.11
     trop
    0.10
     coconut
    0.09
    Activations Density 0.455%

    No Known Activations