© 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. 33172
    Prev
    Next
    INDEX
    Explanations

    pyeloplasty, Chagas', Gumbo, Clarkson, press, Rates, Barber, bandanna

    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
    again
    -0.07
    ä¸Ĭè¿°
    -0.06
     again
    -0.06
    v
    -0.06
     emphas
    -0.06
    iii
    -0.06
    è¿ĺå¤Ħäºİ
    -0.06
    owska
    -0.06
    客
    -0.05
     inilah
    -0.05
    POSITIVE LOGITS
    âĢij
    0.09
     \"
    0.08
    ,\"
    0.08
    tot
    0.08
    EDAD
    0.07
    .\"
    0.07
    ä¸ī两
    0.07
    æĪijåĴĮæĪijçļĦ
    0.07
    为转载
    0.07
     ${(
    0.07
    Activations Density 17.066%

    No Known Activations