© 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. 34143
    Prev
    Next
    INDEX
    Explanations

    sets up examples or conditions

    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
    ä¸Ģå®ļä¼ļ
    -0.08
    好å¿ĥæĥħ
    -0.07
     usually
    -0.07
    åºĶæľīçļĦ
    -0.07
    uzz
    -0.06
    çŃīçĿĢä½ł
    -0.06
     hopefully
    -0.06
     often
    -0.06
    éĤ£å¤´
    -0.06
    ean
    -0.06
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.08
    éĩĩçĶ¨
    0.07
    åĽłåħ¬
    0.07
    çĶ¨æĪ·ä½¿çĶ¨
    0.07
    æī¿åĬŀåįķä½į
    0.07
    åħĪåıij
    0.07
     Kasat
    0.07
    å¹²èĦĨ
    0.07
    èIJ¥éĢłä¸Ģ个
    0.07
    \Input
    0.07
    Activations Density 0.006%

    No Known Activations