© 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. 20542
    Prev
    Next
    INDEX
    Explanations

    some 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
    ä¸Ģç§į
    -0.08
     sexes
    -0.08
    ä¼Ĺå¤ļ
    -0.08
    ä¸ĢåĪĩçļĦ
    -0.08
    çļĦä¸Ģç§įæĸ¹å¼ı
    -0.08
    è¦ģæ±Ĥèĩªå·±
    -0.07
    bele
    -0.07
    ä¸Ģ次次
    -0.07
    æĦŁåıĹçĿĢ
    -0.07
    çļĦä¸Ģç§į
    -0.07
    POSITIVE LOGITS
     wenige
    0.10
    åģļäºĽ
    0.09
    åħ³éĶ®çļĦ
    0.09
    é¢Ŀå¤ĸçļĦ
    0.08
    äºĨ解ä¸Ģä¸ĭ
    0.08
    å¿ħè¦ģçļĦ
    0.08
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    0.08
    åħ¶ä»ĸçļĦ
    0.08
     wenigen
    0.08
    åĩłæĿ¡
    0.08
    Activations Density 0.423%

    No Known Activations