© 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. 7335
    Prev
    Next
    INDEX
    Explanations

    company names and locations

    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
    ä»»ä½ķåªĴä½ĵ
    -0.09
     sao
    -0.08
    çļĦéĩįè¦ģåĽłç´ł
    -0.08
    ä¸įåIJ¬
    -0.08
    社åĮºå±ħæ°ij
    -0.08
    azzo
    -0.08
    æĹı
    -0.08
    åī¥
    -0.08
    ĥĿ
    -0.08
    åħ¶ä»ĸåªĴä½ĵ
    -0.07
    POSITIVE LOGITS
    tika
    0.06
    èī³éĺ³
    0.06
    ikom
    0.06
    å®Ļ
    0.06
    ÉĻt
    0.06
    社éķ¿
    0.06
    inize
    0.05
    åı¸
    0.05
    é¢ĸ
    0.05
     ng
    0.05
    Activations Density 0.140%

    No Known Activations