© 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. 38031
    Prev
    Next
    INDEX
    Explanations

    molecular physics and chemistry

    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
    浪潮
    -0.07
     strat
    -0.07
     hypert
    -0.07
    åĨĽåĮº
    -0.07
    -tier
    -0.06
    æ¶ĪéĢĢ
    -0.06
    wir
    -0.06
    à¹Ģà¸Ļà¸Ńรà¹Į
    -0.06
    uhan
    -0.06
    æ¼ĶçļĦ
    -0.06
    POSITIVE LOGITS
     molecule
    0.11
    olecule
    0.11
     breakup
    0.10
     formation
    0.09
     molecules
    0.09
    åĪĨåŃIJ
    0.08
    éĶ®
    0.08
    åĪĨåŃIJçļĦ
    0.08
     Formation
    0.08
    山谷
    0.08
    Activations Density 0.048%

    No Known Activations