© 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. 29228
    Prev
    Next
    INDEX
    Explanations

    file extensions or specific formats

    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
    itava
    -0.09
    رØŃ
    -0.08
    Ñĥг
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
     Dat
    -0.07
    utang
    -0.07
    Ãło
    -0.07
    วัà¸Ĵ
    -0.06
     Gio
    -0.06
    _cast
    -0.06
    POSITIVE LOGITS
    ;*
    0.07
    å¥
    0.07
    绿
    0.07
     ê²ĥìĿ´ê³ł
    0.06
    æĶ¾è¿ĩ
    0.06
    ignum
    0.06
    ï¼Ľ
    0.06
     Blind
    0.06
    uther
    0.06
    zin
    0.06
    Activations Density 0.129%

    No Known Activations