© 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. 12532
    Prev
    Next
    INDEX
    Explanations

    Shropshire Blue, hybrid-cloud, Rumble Films, Rice Pilaf, constant

    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
    çķĮ
    -0.08
    ilers
    -0.07
    å°ıèĬ±
    -0.07
    ạt
    -0.07
    æī¬
    -0.07
    æıļ
    -0.07
    leb
    -0.07
     Wah
    -0.07
    fol
    -0.07
    uger
    -0.07
    POSITIVE LOGITS
     gan
    0.07
     above
    0.07
    eny
    0.06
    à§ĩà¦ķà§ĩ
    0.06
    à¹Ģà¸ģร
    0.06
    ä¸Ĭè¿°
    0.06
    çŀ»
    0.06
    å¦Ĥä¸Ĭ
    0.06
    umes
    0.06
     maria
    0.06
    Activations Density 0.263%

    No Known Activations