© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44874
    Prev
    Next
    INDEX
    Explanations

    time consuming and expensive

    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
    濯
    -0.08
    ä¾Ŀæ³ķèĩªä¸»
    -0.08
    getResponse
    -0.08
    建工
    -0.08
    PACK
    -0.08
    设计é£İæł¼
    -0.08
    æĶ¾å¿ĥ
    -0.08
    amb
    -0.07
    æĶ¾å¿ĥçļĦ
    -0.07
    ZONE
    -0.07
    POSITIVE LOGITS
     costly
    0.10
     expensive
    0.09
    æĪIJæľ¬é«ĺ
    0.09
     cost
    0.09
    æĺĤè´µ
    0.09
    è´¹çĶ¨
    0.09
    æĪIJæľ¬
    0.09
    æĺĤè´µçļĦ
    0.09
     tá»ijn
    0.09
    è´¹æŶ
    0.08
    Activations Density 0.152%

    No Known Activations