© 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. 41372
    Prev
    Next
    INDEX
    Explanations

    noun followed by preposition

    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
    ç¯ĩä¸Ģ
    -0.07
    åıĬåħ¶å®ĥ
    -0.07
    ç½ij讯
    -0.07
    åį³ä½¿
    -0.07
    yt
    -0.06
     ìĹŃìĭľ
    -0.06
    acen
    -0.06
    sstr
    -0.06
    åį³ä½¿åľ¨
    -0.06
    eron
    -0.06
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.12
    äºĮæĿ¥
    0.09
    äºĮæĺ¯
    0.09
    )|(
    0.09
    äºĮè¦ģ
    0.08
    äºĮæĺ¯è¦ģ
    0.08
    è¿ĺæĺ¯åľ¨
    0.08
    ayet
    0.08
    ude
    0.07
    uckland
    0.07
    Activations Density 0.695%

    No Known Activations