© 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. 60614
    Prev
    Next
    INDEX
    Explanations

    growth medium

    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
     tob
    -0.07
    ê»ĺ
    -0.07
    izen
    -0.07
    adin
    -0.07
    bito
    -0.06
    zeugung
    -0.06
     Thao
    -0.06
    åĮħ饺åŃIJ
    -0.06
    åıįå¼¹
    -0.06
    ãĤ¹ãĥł
    -0.06
    POSITIVE LOGITS
    èIJ¥åħ»ä¸°å¯Į
    0.09
    åIJ«æľī
    0.09
     containing
    0.09
    åŁ¹åħ»åŁº
    0.09
     incub
    0.08
    å¯ĮåIJ«
    0.08
    æ»ĭåħ»
    0.08
     nutrients
    0.08
     conditions
    0.08
    ungan
    0.08
    Activations Density 0.072%

    No Known Activations