© 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. 23566
    Prev
    Next
    INDEX
    Explanations

    numbered lists and sequences

    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
    enza
    -0.08
    ulu
    -0.07
    ben
    -0.07
    èĢ¸
    -0.07
    åłĤ
    -0.07
    ä¸ī年以ä¸Ĭ
    -0.07
    åħ¶äºĮ
    -0.07
    lais
    -0.07
    į°
    -0.06
    loff
    -0.06
    POSITIVE LOGITS
    -ish
    0.07
    -wise
    0.07
    æĬķ稿éĤ®ç®±
    0.07
    wise
    0.07
    _NAMESPACE
    0.06
    æĸŃæ¡¥
    0.06
    æĮ
    0.06
    á»ĭ
    0.06
    è¾ŀ
    0.06
    oundary
    0.06
    Activations Density 0.005%

    No Known Activations