© 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. 40719
    Prev
    Next
    INDEX
    Explanations

    some form of

    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
    æľĢ主è¦ģçļĦ
    -0.08
    isé
    -0.08
    æľĢå¤ļçļĦ
    -0.08
    æīĢ使çĶ¨çļĦ
    -0.07
     demais
    -0.07
    åĵªäºĽ
    -0.07
    åį³ä»¥
    -0.07
    raits
    -0.07
    ekan
    -0.07
    çļĦ第ä¸Ģ个
    -0.07
    POSITIVE LOGITS
     somewhere
    0.11
     else
    0.11
    else
    0.09
     somew
    0.09
     anderem
    0.09
    _else
    0.09
     irgende
    0.08
    åľ¨æŁIJ
    0.08
     irgend
    0.08
    æŁIJç§į
    0.08
    Activations Density 0.206%

    No Known Activations