© 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. 61675
    Prev
    Next
    INDEX
    Explanations

    default actions and organization

    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
    微信åħ¬ä¼Ĺåı·
    -0.07
    Platforms
    -0.07
    èĥ½å¤ŁåģļåĪ°
    -0.07
    æıIJä¾Ľèī¯å¥½çļĦ
    -0.07
    Strict
    -0.07
    微信平åı°
    -0.07
    微信åı·
    -0.07
     instrumentation
    -0.07
    åĪ»çĶ»
    -0.06
    UGHT
    -0.06
    POSITIVE LOGITS
    é»ĺ认
    0.12
     automatically
    0.09
     default
    0.09
    å¿«æį·
    0.08
    é»ĺ认çļĦ
    0.08
    åŃĺ
    0.08
    ä¿ĿåŃĺ
    0.08
     авÑĤомаÑĤиÑĩеÑģки
    0.08
    default
    0.08
     (*.
    0.08
    Activations Density 0.239%

    No Known Activations