© 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. 60213
    Prev
    Next
    INDEX
    Explanations

    scientific theories and existence

    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
    åģ¥åº·ç½ij
    -0.09
    Ñĩей
    -0.08
    ÛĮÙģ
    -0.08
    OMA
    -0.08
    .mc
    -0.07
    æĺ¾ç¤ºçļĦ
    -0.07
     Wanna
    -0.07
    lean
    -0.07
     Pert
    -0.07
    åĽ½éĻħéĩijèŀį
    -0.07
    POSITIVE LOGITS
     scape
    0.08
     ëıĦìŀħ
    0.08
    acr
    0.07
     ÙģÙĥرة
    0.07
     notion
    0.07
     concept
    0.07
    ismus
    0.07
     existence
    0.07
    çŃīæĸ°
    0.07
     postul
    0.07
    Activations Density 0.022%

    No Known Activations