© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2829
    Prev
    Next
    INDEX
    Explanations

    optical isomers, enantiomers, stereochemistry

    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
    lö
    -0.07
     Feinstein
    -0.07
    umpt
    -0.06
    uge
    -0.06
    è¾ĵç»Ļ
    -0.06
    GI
    -0.06
    天åīį
    -0.06
    _che
    -0.06
    çģ¶
    -0.06
    รา
    -0.06
    POSITIVE LOGITS
    åıĮåŁİ
    0.07
    两侧
    0.07
    æīŃ转
    0.07
     decidere
    0.07
    toggleClass
    0.07
    åı¯ä»¥èĩªçĶ±
    0.07
    æľī两个
    0.07
    åĬĽå¼º
    0.07
    rub
    0.07
    Rotation
    0.07
    Activations Density 0.017%

    No Known Activations