© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2406
    Prev
    Next
    INDEX
    Explanations

    question asked

    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
    åĵİ
    -0.08
    èѦå±Ģ
    -0.08
    帮åĬ©ä¸Ńå¿ĥ
    -0.08
    ç¸ģ
    -0.07
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.07
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    -0.07
     finn
    -0.07
    _sess
    -0.07
     Ñĥгодно
    -0.07
    æľĢåIJİæĺ¯
    -0.07
    POSITIVE LOGITS
    iel
    0.07
     Wants
    0.07
     wants
    0.07
     seeks
    0.06
    è¨Ģ
    0.06
    trop
    0.06
     situ
    0.06
     USA
    0.06
    æĥ³è¦ģ
    0.06
    want
    0.06
    Activations Density 0.008%

    No Known Activations