© 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. 12821
    Prev
    Next
    INDEX
    Explanations

    super

    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
    段
    -0.07
    atica
    -0.07
     Fool
    -0.07
    asuk
    -0.06
    å¨ĥå¨ĥ
    -0.06
     Biel
    -0.06
    assistant
    -0.06
     Flo
    -0.06
    ansch
    -0.06
    ä¸įèĥ½ä½¿çĶ¨
    -0.06
    POSITIVE LOGITS
    uzion
    0.09
    andra
    0.09
    ypy
    0.08
    æĶ¾é¡Į
    0.08
    aner
    0.07
    wards
    0.07
    èį¼
    0.07
    redd
    0.07
    aret
    0.07
    urent
    0.07
    Activations Density 0.003%

    No Known Activations