© 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. 62147
    Prev
    Next
    INDEX
    Explanations

    chiral, stereoisomers, enantiomeric

    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
     ver
    -0.08
    OLO
    -0.08
    andes
    -0.07
    åĨ²
    -0.07
    éħįæ¯Ķ
    -0.07
    Feed
    -0.07
    åĨ²è¿Ľ
    -0.07
    èģĮè´£
    -0.07
     impulse
    -0.07
    á»ĩm
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦åħ·æľī
    0.08
     inherent
    0.07
    ä¸įåħ·æľī
    0.07
    åı¯å¯¼èĩ´
    0.07
     locking
    0.07
    éľĢè¦ģèĢĥèĻij
    0.07
    éĺ²èĮĥæݪæĸ½
    0.07
    .Requires
    0.07
    年满
    0.07
    arent
    0.07
    Activations Density 0.004%

    No Known Activations