© 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. 28970
    Prev
    Next
    INDEX
    Explanations

    unusual, unexpected, different, unconventional

    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
    缮å®ī
    -0.08
    urras
    -0.07
    atten
    -0.07
    å¿ħä¸įåı¯å°ijçļĦ
    -0.07
    laz
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    åı¯æģ¶
    -0.07
    å¤ļ好
    -0.07
    äºĨ解ä¼ģä¸ļ
    -0.07
    èĪĴå¿ĥ
    -0.07
    POSITIVE LOGITS
     unusual
    0.17
     unconventional
    0.16
     ungewöhn
    0.15
     неÑģÑĤандаÑĢÑĤ
    0.15
     uncommon
    0.13
     необÑĭ
    0.13
    å¥ĩçī¹
    0.13
     unexpected
    0.12
    èĦ±ä¿Ĺ
    0.12
    ä¸İä¼Ĺä¸įåIJĮçļĦ
    0.12
    Activations Density 0.328%

    No Known Activations