© 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. 42846
    Prev
    Next
    INDEX
    Explanations

    `new` and `conditional` declarations

    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
    ä¹ĻåıĮæĸ¹
    -0.07
    ä¸Ģæĺ¯
    -0.07
    egas
    -0.07
    并åıĬæŶ
    -0.07
    并ä»İ
    -0.06
    ç»ĵä¼´
    -0.06
    并å°Ĩåħ¶
    -0.06
    kw
    -0.06
    çļĦéĩįè¦ģæĢ§åĴĮ
    -0.06
    ãĤĪãģĨãģ§
    -0.06
    POSITIVE LOGITS
     appunto
    0.08
    neos
    0.08
    ä»ĩ
    0.07
     ëĶ°ëĿ¼ìĦľ
    0.07
    upal
    0.07
    rada
    0.07
    roy
    0.07
    代ä¹ĭ
    0.07
    skr
    0.07
     بدÙĪرÙĩ
    0.07
    Activations Density 0.007%

    No Known Activations