© 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. 51831
    Prev
    Next
    INDEX
    Explanations

    integral calculus and momentum space

    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
    è¦ģä¹Ī
    -0.07
    æŃ¥æŃ¥é«ĺ
    -0.06
    èijĹ
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
    å°±åľ°
    -0.06
    é¹
    -0.06
    çĻ¾è²¨
    -0.06
    æķĻ书
    -0.06
    à¶Ńà·Ķ
    -0.06
    _markup
    -0.06
    POSITIVE LOGITS
    空éĹ´åĴĮ
    0.08
    èļ¤
    0.08
    space
    0.08
    akup
    0.08
    ót
    0.08
     пÑĢоÑģÑĤÑĢанÑģÑĤве
    0.08
    çķ
    0.08
    _scope
    0.08
    ç¡
    0.08
    空éĸĵ
    0.08
    Activations Density 0.004%

    No Known Activations