© 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. 21924
    Prev
    Next
    INDEX
    Explanations

    Monte Carlo

    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°±ç®ĹäºĨ
    -0.07
    thon
    -0.07
    UMENT
    -0.06
    åıįåĢĴæĺ¯
    -0.06
     nuanced
    -0.06
     Beij
    -0.06
    å®ŀå®ŀåľ¨
    -0.06
    æĤ£å¤Ħ
    -0.06
    å¹´åħ¨å¹´
    -0.06
    æīĵçĿĢ
    -0.06
    POSITIVE LOGITS
    due
    0.08
     dém
    0.07
    blig
    0.07
    arent
    0.07
    å°Ħ
    0.07
    æijĦ
    0.07
    鸣
    0.07
    LET
    0.07
     due
    0.07
    orat
    0.07
    Activations Density 0.010%

    No Known Activations