© 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. 9359
    Prev
    Next
    INDEX
    Explanations

    . field or san

    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
    ä»ĭ
    -0.06
    ter
    -0.06
    /
    -0.05
    ÙĨاة
    -0.05
    ä¸Ĭãģ®
    -0.05
    pp
    -0.05
    .jupiter
    -0.05
    æ¶ĪéĢĢ
    -0.05
    æ®
    -0.05
    天ä¹ĭ
    -0.05
    POSITIVE LOGITS
    еÑĢÑĭ
    0.08
    xea
    0.08
    ä¸į移
    0.07
    غÙĪ
    0.07
    æĽĻ
    0.07
    çijŀæĭī
    0.07
    agia
    0.07
    ehu
    0.07
    icina
    0.07
    dep
    0.07
    Activations Density 0.002%

    No Known Activations