© 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. 21980
    Prev
    Next
    INDEX
    Explanations

    aqueous

    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
    å®ŀä½ĵ
    -0.07
    eix
    -0.07
    山头
    -0.07
    лÑĥÑĥ
    -0.07
    äººä»¬åľ¨
    -0.07
    emn
    -0.06
    积åĪĨæ¦ľ
    -0.06
    æĹłæīĢè°ĵ
    -0.06
     smak
    -0.06
    çī¹å°Ķ
    -0.06
    POSITIVE LOGITS
    ä¸Ńè¿Ľè¡Į
    0.08
    ä¸Ń被
    0.08
    çݯå¢ĥä¸Ń
    0.08
    ä¸ŃçļĦéĩįè¦ģ
    0.07
    ä¸Ń大
    0.07
    ä¸Ńãģ§
    0.07
    液ä¸Ń
    0.07
    awe
    0.07
    æł¹æį®åħ¶
    0.07
    æĪĸèĢħåħ¶ä»ĸ
    0.07
    Activations Density 0.018%

    No Known Activations