© 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. 38504
    Prev
    Next
    INDEX
    Explanations

    composed of, contains, problem, 've searched, decades, rich, cancer

    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
     übrigens
    -0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
     other
    -0.07
    è¿ĺæľīä¸Ģç§į
    -0.07
     дÑĢÑĥгÑĥÑİ
    -0.07
    æŃ¤ä¸º
    -0.07
    çŃīåħ¶ä»ĸ
    -0.07
    åı¦ä¸Ģ
    -0.07
     дÑĢÑĥгой
    -0.07
    æľĢåIJİæĺ¯
    -0.06
    POSITIVE LOGITS
     ervan
    0.09
     infatti
    0.09
     dabei
    0.09
    å®ĥä¸įä»ħ
    0.09
    ä¸įä»ħèĥ½å¤Ł
    0.09
    itom
    0.08
    omp
    0.08
    å®ĥèĥ½å¤Ł
    0.08
    主è¦ģåĮħæĭ¬
    0.08
     dalamnya
    0.08
    Activations Density 1.471%

    No Known Activations