© 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. 8475
    Prev
    Next
    INDEX
    Explanations

    references with citations

    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
    º
    -0.08
     Lorem
    -0.07
    ouro
    -0.07
    èķĥ
    -0.07
    ÑģÑĮ
    -0.07
    onian
    -0.07
    _recursive
    -0.07
    ogne
    -0.06
    nos
    -0.06
     fou
    -0.06
    POSITIVE LOGITS
    -txt
    0.07
    æĹłæĥħ
    0.07
    è¯ŃéŁ³æŶéķ¿
    0.07
    æĽ¿å°¼
    0.06
    对äºİä¸Ģ个
    0.06
    ucch
    0.06
    æĶ¯éħįæĶ¶åħ¥
    0.06
     iepazÄ«Å¡anÄģs
    0.06
    ÙĦاÙĦ
    0.06
    æľīæŶéĹ´
    0.06
    Activations Density 0.016%

    No Known Activations