© 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. 17597
    Prev
    Next
    INDEX
    Explanations

    time progression

    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
    Configurer
    -0.09
    è¯ķè¯ķåIJ§
    -0.08
    ingleton
    -0.08
    rolet
    -0.07
    ANGAN
    -0.07
    è»Ĵ
    -0.07
    å°ıå°Ĩ
    -0.07
    rohr
    -0.07
    IGGER
    -0.07
    '%
    -0.07
    POSITIVE LOGITS
    æ¼ĶåĮĸ
    0.07
     evolution
    0.07
    endir
    0.07
    chl
    0.07
     elapsed
    0.07
    anns
    0.07
    æ¼Ķ
    0.07
    veau
    0.06
    time
    0.06
    oman
    0.06
    Activations Density 0.016%

    No Known Activations