© 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. 26061
    Prev
    Next
    INDEX
    Explanations

    floor or joint

    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
    æºIJäºİ
    -0.07
    ynn
    -0.07
    æľŁéĻIJ
    -0.06
    ãģ®æµģãĤĮ
    -0.06
    çĽ¸ä¼´
    -0.06
    æºIJè¿ľæµģ
    -0.06
     Gold
    -0.06
     Jr
    -0.06
     Plus
    -0.06
    æĬij
    -0.06
    POSITIVE LOGITS
    KeyType
    0.10
     itib
    0.09
    åħ·æľī丰å¯ĮçļĦ
    0.09
    rece
    0.08
    chenk
    0.08
    åħ¼åħ·
    0.08
    åIJijåѦçĶŁ
    0.07
    avin
    0.07
    å¿Ĺ强
    0.07
    大åĨĻ
    0.07
    Activations Density 0.003%

    No Known Activations