© 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. 23140
    Prev
    Next
    INDEX
    Explanations

    colloidal dimers, metal-organic, particles

    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
    agraph
    -0.08
    amana
    -0.06
    对ä¸Ĭè¿°
    -0.06
    ilst
    -0.06
     *:
    -0.06
    amin
    -0.06
    åĴĮ解
    -0.06
    ↵↵↵
    -0.05
    -awesome
    -0.05
    æĿijä¸Ĭ
    -0.05
    POSITIVE LOGITS
    ä¹Łåıªæľī
    0.08
    åĶ¯æľī
    0.08
    unsch
    0.07
    æīįèĥ½èİ·å¾Ĺ
    0.07
    olik
    0.07
    #/
    0.07
    ManagedObject
    0.07
    Ñijл
    0.07
     %#
    0.07
    ä¹ŁåºĶ该
    0.07
    Activations Density 0.016%

    No Known Activations