© 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. 39263
    Prev
    Next
    INDEX
    Explanations

    analog

    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
    ful
    -0.09
    chas
    -0.09
    odor
    -0.08
    æķĻäºİ
    -0.08
     latter
    -0.08
    fulness
    -0.08
     volna
    -0.08
    ening
    -0.08
    wards
    -0.08
    eral
    -0.08
    POSITIVE LOGITS
    ï¸İ
    0.10
    ously
    0.10
    ues
    0.10
    ous
    0.08
    -minded
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    ledes
    0.08
    æĢ§çļĦ
    0.08
    ège
    0.07
    lave
    0.07
    Activations Density 0.018%

    No Known Activations