© 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. 28304
    Prev
    Next
    INDEX
    Explanations

    dates back, rely on, explained that, demonstrated only

    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
    )))),
    -0.07
     Fass
    -0.07
    ))),
    -0.07
    oot
    -0.07
    桶
    -0.07
    稽
    -0.07
    ä½ĨåIJĮæŶ
    -0.07
    abu
    -0.06
    æĭīéĩĮ
    -0.06
    å¼ĹéĩĮ
    -0.06
    POSITIVE LOGITS
     nonetheless
    0.13
     nevertheless
    0.11
     ändå
    0.10
     dennoch
    0.09
    åį´èĥ½
    0.09
     invece
    0.08
    nowrap
    0.08
    åį»
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    æĽ´èĥ½
    0.08
    Activations Density 0.867%

    No Known Activations