© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    plastid or mitochondria

    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
    åĪĬè½½
    -0.07
     sag
    -0.07
    çĶĺéľ²
    -0.07
    èįŁ
    -0.07
    _abstract
    -0.07
    åıĭæĥħéĵ¾æİ¥
    -0.07
    epage
    -0.07
    æ´Ĵ
    -0.07
    elage
    -0.07
    åľ¨çº¿ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    arus
    0.08
     retained
    0.08
    cred
    0.08
    åŁºåĽłç»Ħ
    0.08
    à¸Īี
    0.07
    leder
    0.07
    emand
    0.07
     mitochond
    0.07
    ä¿ĿçķĻ
    0.07
    åĨħå¤ĸ
    0.07
    Activations Density 0.015%

    No Known Activations