© 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. 3082
    Prev
    Next
    INDEX
    Explanations

    in conjunction with

    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
    ArgumentException
    -0.10
    scht
    -0.09
    ional
    -0.09
    kena
    -0.08
    rena
    -0.08
    mites
    -0.08
    iscal
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    nya
    -0.08
    ç¥Ŀç¦ıä½ł
    -0.07
    POSITIVE LOGITS
    -sama
    0.09
    å®ŀéĻħæĥħåĨµ
    0.09
     nhau
    0.09
    éĿ¢å¹¿
    0.08
    åľ¨ä¸Ģèµ·çļĦ
    0.08
    èµ·æĿ¥çļĦ
    0.07
    iator
    0.07
    ed
    0.07
    Ø·ÙĦ
    0.06
    ancock
    0.06
    Activations Density 0.003%

    No Known Activations