© 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. 40605
    Prev
    Next
    INDEX
    Explanations

    Gaza, cheese, simplicity, interfaces, railways

    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
     upper
    -0.07
    heimer
    -0.07
    TY
    -0.06
    ara
    -0.06
    ä¸įä»ħéľĢè¦ģ
    -0.06
    bro
    -0.06
    iter
    -0.06
    _STEP
    -0.06
    upper
    -0.06
    çī¹å°Ķ
    -0.06
    POSITIVE LOGITS
    ãģĵãĤĮãĤĤ
    0.10
     Lastly
    0.10
    æĥħåĨµçŃī
    0.09
     enfin
    0.09
    è¿ĻäºĽéĥ½
    0.09
     ÑĤоже
    0.08
    管çIJĨçŃī
    0.08
    çŃīçŃī
    0.08
    æ´»åĬ¨çŃī
    0.08
     ãģªãģ©
    0.08
    Activations Density 1.120%

    No Known Activations