© 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. 43763
    Prev
    Next
    INDEX
    Explanations

    around, bridges, kinds, sharp, rise

    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
    labor
    -0.08
    åºĶå½ĵæĮīçħ§
    -0.08
    åIJĮéģĵ
    -0.07
    éĢģæĪij
    -0.07
    estig
    -0.07
    SEN
    -0.07
    argon
    -0.07
    rauch
    -0.07
     spare
    -0.07
    osti
    -0.07
    POSITIVE LOGITS
    è·¨è¶Ĭ
    0.09
    横跨
    0.08
    è¿ŀæİ¥
    0.08
    ÑĸÑĢ
    0.07
    ä¸Ńéĥ¨
    0.07
    æĹłç¼Ŀ
    0.07
    线æĢ§
    0.07
    éĤ£
    0.07
     exported
    0.07
    å¼¥
    0.07
    Activations Density 0.001%

    No Known Activations