© 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. 50138
    Prev
    Next
    INDEX
    Explanations

    continue processing

    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
    olith
    -0.06
    ylon
    -0.06
    pris
    -0.06
     ident
    -0.06
    ugh
    -0.06
    ä¸ĭè½½åĪ°
    -0.06
    åĪĨå¼Ģ
    -0.06
     various
    -0.06
    æł¼å°Ķ
    -0.06
     ad
    -0.06
    POSITIVE LOGITS
    åĨį继ç»Ń
    0.12
    继ç»Ńåľ¨
    0.11
    继ç»Ńè¿Ľè¡Į
    0.11
    继ç»Ń使çĶ¨
    0.10
    继ç»Ń
    0.10
    ç¹¼çºĮ
    0.10
    è¿Ļä¸Ģ次çļĦ
    0.09
     Continue
    0.09
    åIJİç»Ń
    0.09
    继ç»Ńéĺħ读
    0.09
    Activations Density 0.024%

    No Known Activations