© 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. 42549
    Prev
    Next
    INDEX
    Explanations

    ion or generation

    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
    çĽħ
    -0.07
    æĹ©çĨŁ
    -0.06
     arb
    -0.06
    åĪĨ娩
    -0.05
    inator
    -0.05
    å¿
    -0.05
    æŃª
    -0.05
     verv
    -0.05
    arb
    -0.05
    ç´łæĿIJ
    -0.05
    POSITIVE LOGITS
    移è¡Į
    0.10
    ecker
    0.09
    çĽIJåĴĮ
    0.09
    unky
    0.08
    çĬ¶æĢģçļĦ
    0.08
    FILES
    0.08
    转移
    0.08
    ë¦ĩ
    0.08
    ä¸Ģ个个
    0.08
     reside
    0.08
    Activations Density 0.009%

    No Known Activations