© 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. 30725
    Prev
    Next
    INDEX
    Explanations

    either or both

    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
    каÑģ
    -0.07
    orio
    -0.07
    orro
    -0.07
    大åIJĮ
    -0.07
     Shades
    -0.07
    tones
    -0.07
    ÑĩÑĥ
    -0.07
    å·§
    -0.07
    elde
    -0.06
     eclectic
    -0.06
    POSITIVE LOGITS
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    0.16
    åIJĦèĩª
    0.14
    either
    0.14
     begge
    0.13
     either
    0.13
    åIJĦèĩªçļĦ
    0.13
     EITHER
    0.13
    åĪĨåĪ«
    0.13
     BOTH
    0.13
     beide
    0.13
    Activations Density 0.253%

    No Known Activations