© 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. 20944
    Prev
    Next
    INDEX
    Explanations

    making easier decisions

    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
    åIJĭ
    -0.07
    çŁ¥éŁ³
    -0.06
    uela
    -0.06
    ZIA
    -0.06
    iks
    -0.06
    Ûİ
    -0.06
    ANCES
    -0.06
    ÐŀÐŀ
    -0.06
    æľ¬åĽŀçŃĶ
    -0.06
    ÛĮÙĨÚ¯
    -0.06
    POSITIVE LOGITS
    item
    0.08
     (âĢŀ
    0.07
    æĺ¾çĿĢ
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    çĬ¶åĨµ
    0.07
    obet
    0.07
     Cbd
    0.07
     entirety
    0.07
     cbd
    0.07
     Www
    0.07
    Activations Density 0.300%

    No Known Activations