© 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. 25774
    Prev
    Next
    INDEX
    Explanations

    section referencing

    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
    åĬ³
    -0.07
    erez
    -0.07
    溶
    -0.07
    ur
    -0.07
    lander
    -0.07
    ENSE
    -0.07
    lys
    -0.07
    åŁ¼çİī
    -0.07
    äºĨ两
    -0.07
    æĺİ缮
    -0.07
    POSITIVE LOGITS
    é¢ĨèĪª
    0.07
    ä½łèº«è¾¹
    0.07
    ÃīT
    0.07
    è¢«ä½ł
    0.06
    èĩªå·±åĸľæ¬¢çļĦ
    0.06
     Paz
    0.06
    ÙIJÙĥÙİ
    0.06
    对被
    0.06
    梦è§ģ
    0.06
    attro
    0.06
    Activations Density 0.010%

    No Known Activations