© 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. 3330
    Prev
    Next
    INDEX
    Explanations

    A

    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
    alah
    -0.08
    _accessible
    -0.08
    æŶæį·
    -0.07
    Į
    -0.07
    ÙĤاÙĨ
    -0.07
    incu
    -0.07
    rasil
    -0.07
    å¾Ĺèµ·
    -0.07
    tlement
    -0.07
    allee
    -0.07
    POSITIVE LOGITS
    rast
    0.08
    रण
    0.08
    ãĥ£
    0.07
    çļĦåıijçİ°
    0.06
    åĪĹåħ¥
    0.06
    å¹¼ç¨ļ
    0.06
    æ·ij女
    0.06
     fanc
    0.06
    ÛĮ
    0.06
    ouses
    0.06
    Activations Density 0.003%

    No Known Activations