© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39737
    Prev
    Next
    INDEX
    Explanations

    Journal of

    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
    деÑģÑıÑĤ
    -0.08
    æĸ°éĹ»èĪĨæĥħ
    -0.08
    éĺ¶çº§çļĦ
    -0.08
    agno
    -0.08
    ä¸ĭè½½æĬ¥åijĬ
    -0.08
    fyl
    -0.08
    áĥķáĥIJ
    -0.07
    yaj
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    åħ¨éĥ¨è¯Ħ论
    -0.07
    POSITIVE LOGITS
    asikan
    0.08
    åijĺçļĦ
    0.07
    åIJĦé¡¹å·¥ä½ľçļĦ
    0.07
    åķ¥
    0.07
    oz
    0.06
     of
    0.06
    inho
    0.06
    ÃŃces
    0.06
    cip
    0.06
    ÑĨ
    0.06
    Activations Density 0.046%

    No Known Activations