© 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. 23889
    Prev
    Next
    INDEX
    Explanations

    using System

    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
    æŨ
    -0.07
    çIJĨæīĢå½ĵçĦ¶
    -0.06
    inka
    -0.06
    ists
    -0.06
     dash
    -0.06
    amble
    -0.06
     Flight
    -0.06
     flight
    -0.06
     ambit
    -0.06
     dbus
    -0.06
    POSITIVE LOGITS
    fø
    0.08
    trys
    0.08
    é¬Ĩ
    0.07
    кла
    0.07
    fulness
    0.07
     <",
    0.07
    _sensitive
    0.07
    pons
    0.07
    jahres
    0.07
    лл
    0.07
    Activations Density 0.003%

    No Known Activations