© 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. 8831
    Prev
    Next
    INDEX
    Explanations

    spectro/spectral findings

    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
    ement
    -0.09
    sworth
    -0.08
     respeito
    -0.07
    -même
    -0.07
    تز
    -0.07
    istrator
    -0.07
    oves
    -0.07
     ÑģпеÑĨиалиÑģÑĤов
    -0.07
     mạc
    -0.07
    à¹ī
    -0.07
    POSITIVE LOGITS
    acular
    0.09
    ically
    0.09
    illing
    0.08
    ively
    0.08
    er
    0.08
    лÑĮкÑĥ
    0.08
    ORTE
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    æĤ¨åı¯èĥ½
    0.07
    ิà¹īà¸ĩ
    0.07
    Activations Density 0.043%

    No Known Activations