© 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. 13165
    Prev
    Next
    INDEX
    Explanations

    fighting for freedom democracy

    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
    æ¼Ĥ
    -0.06
    Comparator
    -0.06
     practise
    -0.06
    +
    -0.06
    éľĨ
    -0.06
    æĻ®éĢļé«ĺæł¡
    -0.06
    orama
    -0.06
    çĭ¬ç«ĭçļĦ
    -0.06
    马çĶ²
    -0.06
    amis
    -0.06
    POSITIVE LOGITS
    ä¼ĺåĵģ
    0.08
    å¾Ĺ天
    0.08
    ourcem
    0.08
    PerPixel
    0.08
    ablish
    0.07
    íŤ
    0.07
    weets
    0.07
    uetype
    0.07
    æĽ´æĸ°æŶéĹ´
    0.07
    etrics
    0.07
    Activations Density 0.001%

    No Known Activations