© 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. 39345
    Prev
    Next
    INDEX
    Explanations

    relative clauses (who, which)

    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
    èĢĮæĺ¯åĽłä¸º
    -0.08
    éĤ£ä¹ĪçļĦ
    -0.08
    èĢĮåħ¶ä»ĸ
    -0.07
     `,
    -0.07
    èĢĮè¿Ļ
    -0.07
    å·¡åĽŀ
    -0.06
     ÙĪبÙĬÙĨ
    -0.06
    ãģĵãģ¨ãģ§ãģĻ
    -0.06
    ä»Ģ
    -0.06
    æīįè¡Į
    -0.06
    POSITIVE LOGITS
    æķĻèĤ²æĺ¯
    0.10
    è°ĥæŁ¥æĺ¾ç¤º
    0.10
    ients
    0.09
    çļĦäººä¹Ł
    0.09
    çļĦ人éĥ½
    0.09
    åľ°åĿĢä½įäºİ
    0.09
    è´¹çĶ¨çĶ±
    0.08
    çļĦä¸ĢåĪĩéĥ½
    0.08
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    0.08
    çŃīåĿĩ
    0.08
    Activations Density 0.941%

    No Known Activations