© 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. 29778
    Prev
    Next
    INDEX
    Explanations

    incorrect mapping or convention

    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
    iha
    -0.08
    rilla
    -0.08
    tryk
    -0.08
     rajav
    -0.08
    idth
    -0.08
    æĸ¹æĸ¹éĿ¢
    -0.08
    ambang
    -0.08
    å¦Ĥæŀľåıªæĺ¯
    -0.08
    utron
    -0.08
    pio
    -0.07
    POSITIVE LOGITS
    对åºĶ
    0.10
     numbering
    0.10
     positions
    0.09
     naming
    0.09
    ä½įç½®
    0.09
     correspondence
    0.09
     alphabetical
    0.09
     convention
    0.08
     position
    0.08
     correspond
    0.08
    Activations Density 0.024%

    No Known Activations