© 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. 19249
    Prev
    Next
    INDEX
    Explanations

    MP, Tube, healthy, Pian, iband, Running

    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
    main
    -0.06
    -
    -0.06
    -0.06
    om
    -0.06
     '
    -0.06
    ó
    -0.06
    äºĨä¸ĢçĤ¹
    -0.06
     "
    -0.05
    Main
    -0.05
    ä»ĸæīį
    -0.05
    POSITIVE LOGITS
    ugi
    0.10
    culares
    0.09
    hado
    0.09
    avic
    0.09
    '],['
    0.08
    ¹Ħ
    0.08
    WSC
    0.08
    umpl
    0.08
    /dat
    0.08
    ?>>
    0.08
    Activations Density 0.345%

    No Known Activations