© 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. 42257
    Prev
    Next
    INDEX
    Explanations

    Legal citations and copyright notices

    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
    -0.07
    ÏĥÏĩ
    -0.07
    åĮĪçīĻ
    -0.07
    est
    -0.07
    dÃŃ
    -0.07
    egger
    -0.07
    reed
    -0.06
     Concep
    -0.06
    çī¹èī²çļĦ
    -0.06
    /sql
    -0.06
    POSITIVE LOGITS
    ç¥Ģ
    0.07
    ä¸ĢåĽŀäºĭ
    0.07
    ä½Ļåľ°
    0.07
    cala
    0.07
    rale
    0.06
     gái
    0.06
    issa
    0.06
    ERY
    0.06
     dÆ°
    0.06
    धान
    0.06
    Activations Density 0.021%

    No Known Activations