© 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. 49479
    Prev
    Next
    INDEX
    Explanations

    new [token]

    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
    å½ĵæŶçļĦ
    -0.07
    èı²çī¹
    -0.07
    æĺ¯æľĢ
    -0.07
    å¿ĺè¿Ķ
    -0.07
     other
    -0.07
    éĤ£ä¸Ģ
    -0.07
    ulls
    -0.07
    çļĨæľī
    -0.06
    èĩ³ä»Ĭ
    -0.06
    æľĢ常è§ģçļĦ
    -0.06
    POSITIVE LOGITS
    ,new
    0.15
    æĸ°æ°Ķ象
    0.14
    /new
    0.13
    çŃīæĸ°
    0.13
    åĴĮæĸ°
    0.13
    [new
    0.13
    (new
    0.13
    æĸ°çļĦ
    0.13
    æľīæĸ°çļĦ
    0.13
    æĸ°æĸ¹æ³ķ
    0.13
    Activations Density 0.377%

    No Known Activations