© 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. 40444
    Prev
    Next
    INDEX
    Explanations

    without replacement from

    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
    ä½ķåĨµ
    -0.08
    LOT
    -0.07
    åıĺ
    -0.07
     اÙĦÙĪ
    -0.07
    stock
    -0.07
    culo
    -0.07
    odat
    -0.07
    仪
    -0.07
    fact
    -0.07
    (Screen
    -0.07
    POSITIVE LOGITS
    iable
    0.08
    ssen
    0.07
    PARSE
    0.07
    ÌĢ
    0.06
    å½°
    0.06
    åIJĦåľ°çļĦ
    0.06
    ç±³èĬ±
    0.06
    æī«ä¸Ģæī«
    0.06
    è¿Ļæł·çļĦ
    0.06
    涯
    0.06
    Activations Density 0.002%

    No Known Activations