© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    part of, thanks for, based on, on behalf of, when done

    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
    é»ij马
    -0.08
    æŃ¡è¿İ
    -0.08
    gai
    -0.08
    欢è¿İä½ł
    -0.08
    NotFoundException
    -0.08
    ाय
    -0.07
    endt
    -0.07
    amani
    -0.07
    árt
    -0.07
    ä¸ĵäººè´Łè´£
    -0.07
    POSITIVE LOGITS
    aign
    0.07
    ä¸Ĭè¿°
    0.06
     determin
    0.06
    ä¸Ĭæĸĩ
    0.06
    ä¸Ĭè¨ĺ
    0.06
    eln
    0.06
    .ignore
    0.06
    uksi
    0.06
     ,(
    0.06
     da
    0.06
    Activations Density 0.012%

    No Known Activations