© 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. 39953
    Prev
    Next
    INDEX
    Explanations

    electric field

    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
    æ²īéĩį
    -0.08
    æ²īéĩįçļĦ
    -0.07
    åIJŀåIJIJ
    -0.07
    ucket
    -0.07
    éĶĻè¿ĩçļĦ
    -0.06
    ä¹ĸå·§
    -0.06
    สู
    -0.06
    tru
    -0.06
    ivel
    -0.06
    edly
    -0.06
    POSITIVE LOGITS
    -field
    0.09
     field
    0.09
    çĶµåľº
    0.09
     fields
    0.09
    åľº
    0.09
     Field
    0.09
     volts
    0.08
    强度çļĦ
    0.08
    åħĭåĬĽ
    0.08
    Field
    0.08
    Activations Density 0.006%

    No Known Activations