© 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. 49033
    Prev
    Next
    INDEX
    Explanations

    first/last number

    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
    åľ¨ä¸ī
    -0.08
    å¤§çº¦åľ¨
    -0.08
    åľ¨äºĶ
    -0.07
    è¿ijä¸īå¹´
    -0.07
    zett
    -0.07
    itech
    -0.06
    ece
    -0.06
    èĩªåݻ年
    -0.06
    ç¯ĩä¸Ģ
    -0.06
    erville
    -0.06
    POSITIVE LOGITS
     few
    0.10
     two
    0.09
    ï¼ĵ
    0.09
     three
    0.09
     ones
    0.08
    ï¼ķ
    0.08
    ï¼Ķ
    0.08
    ä¸Ģæī¶
    0.08
    ³
    0.08
     five
    0.08
    Activations Density 0.062%

    No Known Activations