© 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. 27606
    Prev
    Next
    INDEX
    Explanations

    average level of things

    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
    祥
    -0.08
    æ´ĭ
    -0.08
    以åѦçĶŁ
    -0.07
    ongoose
    -0.07
    çĶ±ä¸ŃåĽ½
    -0.07
    bos
    -0.07
    ToLocal
    -0.07
    дж
    -0.07
    价为
    -0.07
    èĸª
    -0.07
    POSITIVE LOGITS
     chia
    0.07
    æµģåħī
    0.07
    ifter
    0.07
    ä¸įåIJĪ
    0.06
     divided
    0.06
    çĤ®å¼¹
    0.06
    omit
    0.06
    ×Ļ׾×ķ
    0.06
     pa
    0.06
     splits
    0.06
    Activations Density 0.002%

    No Known Activations