© 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. 41263
    Prev
    Next
    INDEX
    Explanations

    days of the week, dates

    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
    æĿ¥å¹´
    -0.09
    å¤ı天
    -0.08
    å¹´å§ĭ
    -0.08
    æĹºåŃ£
    -0.08
    iett
    -0.08
    åĴĮæݧåĪ¶
    -0.07
    è¿ĩåĨ¬
    -0.07
    RATION
    -0.07
    ä¸įæŃ£
    -0.07
    jord
    -0.07
    POSITIVE LOGITS
    abend
    0.08
    midd
    0.08
    -feira
    0.07
    Å¡nj
    0.07
    nesday
    0.07
    arrant
    0.06
    åĦ¿åª³
    0.06
    夫婦
    0.06
    inga
    0.06
    etch
    0.06
    Activations Density 0.120%

    No Known Activations