© 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. 29552
    Prev
    Next
    INDEX
    Explanations

    age descriptor

    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
    å°ijå¹´åĦ¿ç«¥
    -0.07
    ä»Ĩ
    -0.07
    ä¸ĵ家åѦèĢħ
    -0.06
    å°ı家ä¼Ļ
    -0.06
     Patr
    -0.06
    çī¹
    -0.06
    è¿Ļä¸ľè¥¿
    -0.06
    ringe
    -0.06
    rase
    -0.06
    大人
    -0.06
    POSITIVE LOGITS
    æĥħå¢ĥ
    0.09
    æ¡Īä¾ĭ
    0.09
    åĮĸåIJį
    0.09
     fict
    0.09
    çļĦæ¡Īä¾ĭ
    0.09
     scenario
    0.08
    XYZ
    0.08
    scenario
    0.08
    @example
    0.08
     اÙĦÙħثاÙĦ
    0.08
    Activations Density 0.279%

    No Known Activations