© 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. 27360
    Prev
    Next
    INDEX
    Explanations

    lust, greed, pleasure, wants

    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
    otope
    -0.08
     traumatis
    -0.08
    æı´æľĿ
    -0.08
    èĦĬæ¤İ
    -0.07
     spia
    -0.07
     Dias
    -0.07
    odate
    -0.07
    ocode
    -0.07
    ÙĤع
    -0.07
    BuilderInterface
    -0.07
    POSITIVE LOGITS
    æ¬²æľĽ
    0.14
    享ä¹IJ
    0.13
     indul
    0.11
    æĶ¾çºµ
    0.11
    诱æĥij
    0.10
    æħ¾
    0.10
     greed
    0.10
     passions
    0.10
    è´ª
    0.10
     unchecked
    0.10
    Activations Density 0.032%

    No Known Activations