© 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. 25520
    Prev
    Next
    INDEX
    Explanations

    manufacturing

    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
    ัà¸į
    -0.09
    opsis
    -0.09
    NECT
    -0.09
    ì¹Ń
    -0.08
     بÙĨدÛĮ
    -0.08
    naires
    -0.08
    ież
    -0.08
     tán
    -0.08
    aire
    -0.08
     demais
    -0.08
    POSITIVE LOGITS
    adora
    0.07
    åĴĮéĶĢåĶ®
    0.07
    å¼ºåĽ½
    0.07
    /man
    0.07
    олÑĮ
    0.07
    ç²¾èī¯
    0.06
    urers
    0.06
    ä¹ĭæģ©
    0.06
    æĢ»å±Ģ
    0.06
    enster
    0.06
    Activations Density 0.043%

    No Known Activations