© 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. 32241
    Prev
    Next
    INDEX
    Explanations

    starting from

    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
    ä¹ĭçĶ¨
    -0.07
    å·
    -0.07
    å±Ĭ
    -0.07
    æĬĢæľ¯çļĦåºĶçĶ¨
    -0.07
    æŀ
    -0.06
     Dra
    -0.06
    singleton
    -0.06
    hers
    -0.06
    ffet
    -0.06
    åIJĪä½ľçĶ¨
    -0.06
    POSITIVE LOGITS
    definitions
    0.08
     definitions
    0.08
    åİŁå§ĭçļĦ
    0.08
     basics
    0.08
     иÑģÑħод
    0.08
    ä¸įå¿į
    0.07
     поÑģÑĤÑĥ
    0.07
    æľĢåŁºæľ¬
    0.07
    åİŁæľ¬çļĦ
    0.07
     originally
    0.07
    Activations Density 0.014%

    No Known Activations