© 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. 48900
    Prev
    Next
    INDEX
    Explanations

    ramified cover, squaring, arithmetic circuits, biased framework, characteristic

    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
    иÑĢ
    -0.08
    ieras
    -0.08
    æľīæĥħ
    -0.08
    åĢ©
    -0.08
    ainty
    -0.07
     Feinstein
    -0.07
    iera
    -0.07
    .ru
    -0.07
    æľīèī²
    -0.07
    orex
    -0.07
    POSITIVE LOGITS
    èĭŁ
    0.09
     stutter
    0.07
    æij©
    0.07
    å¹Ĥ
    0.07
    ledon
    0.07
     Dou
    0.07
     mon
    0.07
    ooth
    0.07
    hus
    0.06
    arten
    0.06
    Activations Density 0.003%

    No Known Activations