© 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. 2021
    Prev
    Next
    INDEX
    Explanations

    development of, what is, I'm

    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
    ucker
    -0.08
    culus
    -0.07
    ç°§
    -0.07
    æĸ°é«ĺ
    -0.07
    _subtype
    -0.07
    æĢ
    -0.07
    _MR
    -0.06
    inesi
    -0.06
    pring
    -0.06
    opped
    -0.06
    POSITIVE LOGITS
    管çIJĨæĸ¹éĿ¢
    0.08
    çĦ¶åIJİæĺ¯
    0.08
    æķ´ä½ĵ
    0.08
    åħ¶ä»ĸçļĦ
    0.08
     пÑĢоÑĩие
    0.07
     пÑĢоÑĩиÑħ
    0.07
    åķıé¡Įãģ¯
    0.07
     Other
    0.07
    æķ´ä½ĵçļĦ
    0.07
    åĨįçľĭ
    0.07
    Activations Density 0.025%

    No Known Activations