© 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. 22677
    Prev
    Next
    INDEX
    Explanations

    materials, gems, and compounds

    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
     timed
    -0.07
     revamped
    -0.07
    ìĪł
    -0.07
    Gear
    -0.06
    ä¸įæ¼ı
    -0.06
    ä¼łåĩº
    -0.06
    模æĭŁ
    -0.06
    å¹²æ´Ĺ
    -0.06
     Clothes
    -0.06
    æĴŃ
    -0.06
    POSITIVE LOGITS
    åĪĩåī²
    0.12
    æĭ¼æİ¥
    0.09
     наÑĢезаÑĤÑĮ
    0.09
    æī¹æ¬¡
    0.09
    ä½ľåºŁ
    0.09
    åĪĩæĪIJ
    0.09
    å¹³æķ´
    0.09
    åĪĩçīĩ
    0.09
    _USED
    0.09
    åı¯çĶ¨äºİ
    0.09
    Activations Density 0.127%

    No Known Activations