© 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. 57266
    Prev
    Next
    INDEX
    Explanations

    after start, want, and let

    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
    æĺ¯ä¸Ģ个人
    -0.09
    ä½łçľŁçļĦ
    -0.08
    æ¯Ķå¦Ĥ说
    -0.07
    æµ·ä¸ľ
    -0.07
    åħ¶ä»ĸåªĴä½ĵ
    -0.07
    ืà¸Ńà¸Ļ
    -0.07
    онаÑĤ
    -0.07
    à¹ĩà¸ļ
    -0.07
    rosa
    -0.07
    utr
    -0.07
    POSITIVE LOGITS
     applying
    0.08
     correspond
    0.07
    å°Ĩè¿ij
    0.07
    åľ¨
    0.07
    ãģĻãĤĭãģ¨
    0.06
    atsu
    0.06
    åĩŃçĿĢ
    0.06
    åı¯å¾Ĺ
    0.06
    "><!--
    0.06
    以ä¸Ĭ
    0.06
    Activations Density 0.002%

    No Known Activations