© 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. 42638
    Prev
    Next
    INDEX
    Explanations

    fortunate to serve

    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
    åIJĴ
    -0.07
    ä¹Łåı«
    -0.07
    agnol
    -0.07
    æľīåı¯èĥ½
    -0.06
    åīĬ
    -0.06
    <|box_end|>
    -0.06
    ä¸Ķæľī
    -0.06
    çī¹åĪ¥
    -0.06
     funny
    -0.06
    ÑģÑĤÑı
    -0.06
    POSITIVE LOGITS
    rium
    0.07
    å¦Ĥåıijçİ°
    0.07
    åĪĩåĭ¿
    0.07
    Adr
    0.07
    æĵįä½ľä¸Ĭ
    0.07
    æľĢ为
    0.07
    å¦Ĥä¸Ĭ
    0.07
     broadly
    0.07
    笼
    0.07
    æĪIJçĨŁçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations