© 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. 12775
    Prev
    Next
    INDEX
    Explanations

    how to find

    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
    ily
    -0.07
     lieber
    -0.07
    akta
    -0.07
    udit
    -0.06
    åĨĴçĿĢ
    -0.06
    enez
    -0.06
    以ä¸ĭ为
    -0.06
    社ä¼ļåĮĸ
    -0.06
    å¿ħ须符åIJĪ
    -0.06
    µ
    -0.06
    POSITIVE LOGITS
    åĴĮçIJĨ解
    0.09
    cke
    0.08
    æĨ¬
    0.08
    اط
    0.08
    ange
    0.08
    è¿ĻäºĽä¿¡æģ¯
    0.07
    å±ħæĺĵ
    0.07
    etts
    0.07
    éħįæĪ´
    0.07
    aval
    0.07
    Activations Density 0.076%

    No Known Activations