© 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. 30872
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and calculations

    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
    igs
    -0.08
    .sep
    -0.07
    åĸ³åĸ³
    -0.07
    ibly
    -0.06
    ULLET
    -0.06
    æ·ĩ
    -0.06
     Shawn
    -0.06
     못íķł
    -0.06
    iful
    -0.06
    -/
    -0.06
    POSITIVE LOGITS
    inia
    0.07
    .inject
    0.07
    Inspector
    0.07
    kast
    0.07
    aska
    0.07
    exual
    0.07
    luv
    0.07
    niku
    0.07
    acked
    0.07
    akra
    0.06
    Activations Density 0.025%

    No Known Activations