© 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. 14607
    Prev
    Next
    INDEX
    Explanations

    complex form

    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
     Pani
    -0.07
    urgo
    -0.07
    å¬
    -0.06
    åıĬå®īåħ¨
    -0.06
    è¿Ļ个æķħäºĭ
    -0.06
    建ç«ĭäºĨ
    -0.06
    tle
    -0.06
    otá
    -0.06
    Ñĥме
    -0.06
    ä¸įä¹ı
    -0.06
    POSITIVE LOGITS
    çīĪ
    0.12
     version
    0.11
    çīĪçļĦ
    0.11
     counterpart
    0.09
     versions
    0.09
    _version
    0.09
    çīĪæľ¬
    0.09
    çīĪæľ¬çļĦ
    0.08
     ë²ĦìłĦ
    0.08
    ujur
    0.08
    Activations Density 0.026%

    No Known Activations