© 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. 28266
    Prev
    Next
    INDEX
    Explanations

    power supply current

    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
    HUD
    -0.08
     hatch
    -0.07
    对çħ§
    -0.07
    为人们
    -0.07
    赤
    -0.07
    _STANDARD
    -0.06
    æĹłç¼ĿéĴ¢ç®¡
    -0.06
    LBL
    -0.06
    êt
    -0.06
     ethn
    -0.06
    POSITIVE LOGITS
     impedance
    0.12
    éĺ»æĬĹ
    0.11
     supply
    0.10
     Supply
    0.10
    supply
    0.10
    Supply
    0.09
     capacit
    0.09
     supplying
    0.08
    ä¾ĽåºĶ
    0.08
    -load
    0.08
    Activations Density 0.041%

    No Known Activations