© 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. 19452
    Prev
    Next
    INDEX
    Explanations

    cancel, terminate, end, or finish

    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
    ä¸Ń磩
    -0.07
    igon
    -0.07
    èĢĮéĤ£äºĽ
    -0.07
    AGEN
    -0.07
    æijĺæĬĦ
    -0.07
    ourced
    -0.07
     hÃŃ
    -0.06
     spared
    -0.06
    ernet
    -0.06
    æĶ¶éĽĨçļĦ
    -0.06
    POSITIVE LOGITS
    解éĻ¤
    0.09
    æĹłåīį
    0.08
    æ¶Ī
    0.08
    éĤ®
    0.07
    æģ¢å¤įæŃ£å¸¸
    0.07
    ç¡ķ
    0.07
     Kra
    0.07
     háºŃu
    0.07
     kay
    0.06
     postfix
    0.06
    Activations Density 0.003%

    No Known Activations