© 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. 50535
    Prev
    Next
    INDEX
    Explanations

    spread spectrum communication

    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
    нÑģ
    -0.08
    åŁ
    -0.08
    ãĥ³ãĥī
    -0.07
    åijĺçļĦ
    -0.07
     Raya
    -0.07
    ikat
    -0.07
    /games
    -0.07
    yku
    -0.07
    /message
    -0.07
    Ñİн
    -0.07
    POSITIVE LOGITS
    æĬĢæľ¯çļĦåºĶçĶ¨
    0.07
    ievo
    0.07
    -style
    0.07
    åĴĮéĿŀ
    0.07
    ä¹łè¿ijå¹³æĢ»ä¹¦è®°åľ¨
    0.06
    (reverse
    0.06
    åĴĮæľ¬
    0.06
    -type
    0.06
    /on
    0.06
    åĴĮåIJİ
    0.06
    Activations Density 0.311%

    No Known Activations