© 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. 22913
    Prev
    Next
    INDEX
    Explanations

    one size fits all

    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
    强度åĴĮ
    -0.08
    åĵ¥çļĦ
    -0.07
    uch
    -0.07
    ç¥ŀä¹ĭ
    -0.07
    ekl
    -0.06
    ÙĨÙĬØ©
    -0.06
    å±ĤéĿ¢ä¸Ĭ
    -0.06
    å´İå¸Ĥ
    -0.06
    arani
    -0.06
    å¹²åĩĢæķ´æ´ģ
    -0.06
    POSITIVE LOGITS
    åħ®
    0.08
    ç»´å¥ĩ
    0.07
    ÎŃÏģα
    0.07
     orto
    0.07
    ego
    0.07
    Ø°Ùİا
    0.07
    idea
    0.07
    åįĩåĪĿ
    0.06
    èĤ²æīį
    0.06
    åľ°å®ĮæĪIJ
    0.06
    Activations Density 0.026%

    No Known Activations