© 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. 27624
    Prev
    Next
    INDEX
    Explanations

    combination of parameters

    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
    害
    -0.08
    ä¸Ĭè¿°äºĭå®ŀ
    -0.07
    æ²¿æ±Ł
    -0.07
    essi
    -0.07
    aud
    -0.06
    vre
    -0.06
    ç»´äºļ
    -0.06
    xDC
    -0.06
    第ä¸Ģ线
    -0.06
    éľĩåĬ¨
    -0.06
    POSITIVE LOGITS
    山人
    0.08
    æĢ»åĪĨ
    0.08
    .plist
    0.07
    lej
    0.07
    fran
    0.07
    å¾Ļ
    0.07
    anse
    0.07
    ìļ°
    0.07
    itrust
    0.07
    ked
    0.07
    Activations Density 0.002%

    No Known Activations