© 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. 41620
    Prev
    Next
    INDEX
    Explanations

    I am trying to

    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
    ambo
    -0.08
    oze
    -0.07
    Ùĩاز
    -0.07
    ä¸ĢåĪ°
    -0.06
    åĴĮåŁºæľ¬
    -0.06
    sud
    -0.06
    odz
    -0.06
    çŁ³æŁ±
    -0.06
    arro
    -0.06
     tuk
    -0.06
    POSITIVE LOGITS
    asser
    0.08
    bara
    0.08
    loff
    0.07
    æ¯ķç«Łæĺ¯
    0.07
    uss
    0.07
     pomi
    0.07
    ä¸įå°ıå¿ĥ
    0.07
    æĥ³è®©
    0.07
    igg
    0.07
    -ignore
    0.07
    Activations Density 0.011%

    No Known Activations