© 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. 20196
    Prev
    Next
    INDEX
    Explanations

    .html, .kitchen.yml, makefile

    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
    åıij表è¯Ħ论
    -0.07
    lipp
    -0.07
    丹éĿĴ
    -0.07
    blo
    -0.07
    rul
    -0.07
    íı¬ì¸ł
    -0.07
    idd
    -0.07
    æ°ĵ
    -0.06
    멤
    -0.06
    TagName
    -0.06
    POSITIVE LOGITS
     vang
    0.07
     Climat
    0.07
    ibbon
    0.06
    æĿľ
    0.06
    éľ²åĩºä¸Ģ
    0.06
    å¥ij
    0.06
    ÑĪев
    0.06
    ضاÙģ
    0.06
    izona
    0.06
    èµĦ
    0.06
    Activations Density 0.535%

    No Known Activations