© 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. 39893
    Prev
    Next
    INDEX
    Explanations

    illuminated, bulbs, bra, components, cord, endodontic

    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
    Idle
    -0.07
     inaugur
    -0.07
     stumbling
    -0.07
     idle
    -0.07
    åIJĿ
    -0.06
    æ·³
    -0.06
     Idle
    -0.06
    rim
    -0.06
    éĹ²ç½®
    -0.06
    é£İå°ĺ
    -0.06
    POSITIVE LOGITS
     inside
    0.20
    åľ¨éĩĮéĿ¢
    0.19
    inside
    0.18
     underneath
    0.18
    Inside
    0.17
     внÑĥÑĤÑĢи
    0.16
     Inside
    0.16
    åĨħéĥ¨
    0.15
    åĨħéĥ¨çļĦ
    0.15
     interno
    0.15
    Activations Density 0.580%

    No Known Activations