© 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. 3540
    Prev
    Next
    INDEX
    Explanations

    comparison phrase ending

    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
    çļĦ人äºĨ
    -0.09
    æĹ¢åı¯
    -0.08
    è¨Ģä¹ĭ
    -0.08
    ä¸įæŃ»
    -0.07
    ĮĢ
    -0.07
    å°±æĺ¯è¿Ļä¹Ī
    -0.07
    åIJİ被
    -0.07
    ting
    -0.07
    å°±æĺ¯äºĨ
    -0.07
    mitt
    -0.07
    POSITIVE LOGITS
    åĪĻä¼ļ
    0.11
    çļĦè¯Ŀ
    0.11
    åĪĻ为
    0.10
    åĪĻ
    0.10
    åĪĻçĶ±
    0.10
    åĪĻ以
    0.10
    åĪĻåľ¨
    0.09
     thì
    0.09
    éĤ£ä½łå°±
    0.09
    åĪĻå°Ĩ
    0.08
    Activations Density 0.050%

    No Known Activations