© 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. 9253
    Prev
    Next
    INDEX
    Explanations

    retrospective observational studies

    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
    ÑĩаÑģÑĤ
    -0.08
    _STORAGE
    -0.07
    ÑĢÑĥз
    -0.07
    agina
    -0.07
    usu
    -0.07
    æĺİç¡®è¦ģæ±Ĥ
    -0.07
    ä¿Ŀé²ľ
    -0.07
    å®ŀä½ĵç»ıæµİ
    -0.07
    å®ŀä¸ļæľīéĻIJåħ¬åı¸
    -0.07
    红红çļĦ
    -0.07
    POSITIVE LOGITS
    éĹ´æİ¥
    0.14
     indirect
    0.12
     indire
    0.10
     indirectly
    0.09
     proxies
    0.08
     relies
    0.08
    åĩŃ
    0.08
     relying
    0.08
     rely
    0.08
     INDIRECT
    0.08
    Activations Density 0.139%

    No Known Activations