© 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. 56538
    Prev
    Next
    INDEX
    Explanations

    states that

    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
    elter
    -0.08
    ($)
    -0.08
    eld
    -0.07
    è°ĵä¹ĭ
    -0.07
     dons
    -0.07
     túc
    -0.07
    åĬłåħ¥æĶ¶èĹı
    -0.07
    ç§ijæĬĢåѦéĻ¢
    -0.07
    ÙħÙĥÙĨ
    -0.07
    ERRU
    -0.07
    POSITIVE LOGITS
    igan
    0.06
    æķ´æķ´
    0.06
    igno
    0.06
    eree
    0.06
    cano
    0.06
    anam
    0.06
    baum
    0.06
     ↵
    0.06
    ä¸ĢæŦåıijçİ°
    0.06
    ffy
    0.06
    Activations Density 0.068%

    No Known Activations