© 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. 30491
    Prev
    Next
    INDEX
    Explanations

    makes them able to be set

    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
    ingers
    -0.08
    ä¸Ģ次
    -0.07
    ä½ļåIJį
    -0.07
    пом
    -0.07
    ä¸įæĥ³
    -0.06
     happ
    -0.06
    人äºĨ
    -0.06
     Gors
    -0.06
     bothered
    -0.06
    æİ¥çĿĢ
    -0.06
    POSITIVE LOGITS
     extensively
    0.08
    weis
    0.08
    ilah
    0.08
    swire
    0.07
    Logged
    0.07
    elage
    0.07
    è¯ī
    0.07
    è°£
    0.07
    zerű
    0.07
    åĨħåľ°
    0.07
    Activations Density 0.242%

    No Known Activations