© 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. 28799
    Prev
    Next
    INDEX
    Explanations

    your fantasies and dreams

    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
    icola
    -0.07
    (rv
    -0.07
    åĴĮ第
    -0.07
    ÙĪرا
    -0.07
    ä¸½å¨ľ
    -0.06
    ussin
    -0.06
    icos
    -0.06
    纳德
    -0.06
    äºĨè¿Ļä¸Ģ
    -0.06
    erein
    -0.06
    POSITIVE LOGITS
    afd
    0.07
    /font
    0.06
    hum
    0.06
    ÏģίÏĤ
    0.06
     woll
    0.06
    éĢļ讯å½ķ
    0.06
    anno
    0.06
    åı¯æĥ³
    0.06
    ĺ
    0.06
    egl
    0.06
    Activations Density 1.174%

    No Known Activations