© 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. 65435
    Prev
    Next
    INDEX
    Explanations

    PA RICK ID FRIEND ALL ON QU CHO IB AF IN

    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
    ä»¤ä½ł
    -0.07
    èĢĮéĻį
    -0.07
    åħľ
    -0.07
    ,number
    -0.07
     ÐŁÐ¾Ð¿ÑĢо
    -0.06
    jes
    -0.06
    ä¸Ŀ带
    -0.06
    è¿ĺæľīçĿĢ
    -0.06
    ä¹Łä¸įç®Ĺ
    -0.06
    èĢĮéĢłæĪIJ
    -0.06
    POSITIVE LOGITS
    تÙĩ
    0.07
    alti
    0.07
    çĶŁåľ¨
    0.06
     ÑģебÑı
    0.06
    aston
    0.06
    гÑĥÑĢ
    0.06
    ä¼ij
    0.06
    çĶŁ
    0.06
    lair
    0.06
    éĤģ
    0.06
    Activations Density 0.601%

    No Known Activations