© 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. 42653
    Prev
    Next
    INDEX
    Explanations

    dipole, polarity, static charge

    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
    isson
    -0.08
     глад
    -0.08
    ldata
    -0.08
    á»ijt
    -0.07
    'er
    -0.07
    émat
    -0.07
    agal
    -0.07
    yder
    -0.07
    éĻIJè´Ń
    -0.07
     subsequ
    -0.07
    POSITIVE LOGITS
     polarity
    0.10
    æŀģæĢ§
    0.08
    çŁ¢éĩı
    0.08
     dip
    0.08
     vector
    0.07
    æ´ģ
    0.07
    çļĦåIJĪæĪIJ
    0.07
    è¿Ľä¸ĢæŃ¥å¢ŀ强
    0.07
     resultant
    0.07
     asym
    0.07
    Activations Density 0.001%

    No Known Activations