© 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. 42168
    Prev
    Next
    INDEX
    Explanations

    conformational analysis and descriptors

    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
    ç£ħ
    -0.07
     Daya
    -0.07
    кÑĢа
    -0.06
    éĩijçŁ³
    -0.06
    è¡Ģæ¸ħ
    -0.06
    adiator
    -0.06
    ufa
    -0.06
    ©
    -0.06
    شارة
    -0.06
    çīĮçħ§
    -0.06
    POSITIVE LOGITS
     comfortably
    0.08
    èĪĴæľįçļĦ
    0.07
     orientations
    0.07
     Newman
    0.07
    è°ļ
    0.07
    odoro
    0.07
     prefers
    0.07
    ä¼¸çĽ´
    0.07
     rotations
    0.07
    uai
    0.07
    Activations Density 0.008%

    No Known Activations