© 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. 21482
    Prev
    Next
    INDEX
    Explanations

    registered in England and Wales

    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
    åħ¬åħ±èµĦæºIJ交æĺĵä¸Ńå¿ĥ
    -0.07
    æĴĴä¸Ĭ
    -0.07
    æĸ°ä¹¦æݨèįIJ
    -0.07
    usher
    -0.07
    pgsql
    -0.07
    å¼ĥ
    -0.07
     xá
    -0.07
    ç²¾çĤ¼
    -0.07
    è·Łè´´
    -0.07
    被æ·ĺæ±°
    -0.07
    POSITIVE LOGITS
    è´°
    0.07
     Notice
    0.07
    æī¹å¤į
    0.07
    äºĮä½į
    0.07
    å¤ĩæ¡Ī
    0.07
    许åı¯
    0.07
    notice
    0.07
     registre
    0.07
    anakan
    0.07
    å±Ĩ
    0.07
    Activations Density 0.098%

    No Known Activations