© 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. 17195
    Prev
    Next
    INDEX
    Explanations

    spirocyclic, adamantyl, cage structures

    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
    ÏĢÏī
    -0.08
    æĢĴäºĨ
    -0.07
    ATO
    -0.07
    ewise
    -0.07
     Äijuôi
    -0.07
    éľĸ
    -0.07
    髦
    -0.07
    稼
    -0.07
    fass
    -0.06
    est
    -0.06
    POSITIVE LOGITS
     structures
    0.09
    structure
    0.09
    ç»ĵæŀĦ
    0.09
     구조
    0.09
    structures
    0.09
    ç»ĵæŀĦçļĦ
    0.09
    ç»ĵæŀĦä¸İ
    0.08
     Strukturen
    0.08
    çµIJæ§ĭ
    0.08
     structure
    0.08
    Activations Density 0.012%

    No Known Activations