© 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. 63324
    Prev
    Next
    INDEX
    Explanations

    selected items or categories

    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
    æī¾ä¸ª
    -0.08
    arkin
    -0.08
    iran
    -0.07
    imbang
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
    è¿ĺæĺ¯æ²¡æľī
    -0.07
    ãĤĦãģı
    -0.07
    .Comparator
    -0.07
    åħ«æĸ¹
    -0.07
    åIJĦç»Ħ
    -0.07
    POSITIVE LOGITS
    åĵªäºĽ
    0.18
    æľīåĵªäºĽ
    0.12
    åĵªäºĽæĸ¹éĿ¢
    0.12
    å¤ļéĢīé¢ĺ
    0.11
    å¤ļéĢī
    0.11
    åĩ¡æĺ¯
    0.10
    åĵªäºĽéĹ®é¢ĺ
    0.08
     BOTH
    0.08
     ones
    0.08
    éĥ½æľīåĵªäºĽ
    0.08
    Activations Density 0.152%

    No Known Activations