© 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. 25404
    Prev
    Next
    INDEX
    Explanations

    up to

    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
    edio
    -0.07
     تÙĤرÙĬب
    -0.07
     Bal
    -0.07
    æļĤæĹ¶æ²¡æľī
    -0.07
    jal
    -0.07
     faj
    -0.07
    ollen
    -0.06
    yna
    -0.06
    ç·ļä¸Ĭ
    -0.06
    etal
    -0.06
    POSITIVE LOGITS
    æľ¬æ³ķ
    0.08
    éĹŃå¹ķå¼ı
    0.07
    sher
    0.07
    èģ
    0.07
     Governors
    0.07
    elo
    0.07
    ä½Ĩä¸įè¦ģ
    0.07
    itam
    0.07
    ÙĬرÙĪ
    0.07
     Ðļл
    0.06
    Activations Density 0.057%

    No Known Activations