© 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. 31317
    Prev
    Next
    INDEX
    Explanations

    ATP synthase and generator

    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
     airing
    -0.07
    _PUR
    -0.07
    volu
    -0.07
    unc
    -0.07
    åĸ·æ¼Ĩ
    -0.07
     ХаÑĢакÑĤеÑĢиÑģÑĤики
    -0.07
    ysh
    -0.07
     Wich
    -0.07
     ÑħаÑĢакÑĤеÑĢиÑģÑĤики
    -0.07
    oon
    -0.07
    POSITIVE LOGITS
    طر
    0.08
     generator
    0.07
    ç²
    0.07
    åıijçĶµ
    0.07
    è¿Ľåĩº
    0.07
    æĺ¯åĪ©çĶ¨
    0.07
    oldem
    0.07
    åĪ©çĶ¨å¥½
    0.06
     Reverse
    0.06
    èĢ¦
    0.06
    Activations Density 0.022%

    No Known Activations