© 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. 11119
    Prev
    Next
    INDEX
    Explanations

    stereochemistry, configuration, directions, assignment

    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
    undur
    -0.09
    ooth
    -0.08
    burgh
    -0.07
    -stats
    -0.07
    åļ
    -0.07
    Statistic
    -0.07
    æ¾İæ¹ĸ
    -0.07
     vok
    -0.07
    lev
    -0.07
    ITS
    -0.07
    POSITIVE LOGITS
     designation
    0.09
    åij½åIJį
    0.09
     labeling
    0.09
     mnemonic
    0.09
     labels
    0.08
     notation
    0.08
     label
    0.07
    åij½åIJį为
    0.07
     assignment
    0.07
     initials
    0.07
    Activations Density 0.002%

    No Known Activations