© 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. 22313
    Prev
    Next
    INDEX
    Explanations

    breakdown field voltage 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
     anthrop
    -0.07
    ril
    -0.07
    å¸ĸ
    -0.06
    人类
    -0.06
    çĨ
    -0.06
    é¦Ĩ
    -0.06
     Anthrop
    -0.06
     Wik
    -0.06
    èł
    -0.06
    çĥŃåĬĽ
    -0.06
    POSITIVE LOGITS
    vad
    0.10
    isert
    0.08
    .ReadOnly
    0.08
    داد
    0.08
    ihal
    0.08
    sville
    0.08
    Sizes
    0.08
    лма
    0.08
    kite
    0.08
    olithic
    0.07
    Activations Density 0.004%

    No Known Activations