© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27041
    Prev
    Next
    INDEX
    Explanations

    č followed by comment characters

    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
    inc
    -0.08
    æĦŁåıĹçĿĢ
    -0.07
    enton
    -0.07
    nip
    -0.07
    aus
    -0.07
    ÏģÏīÏĥη
    -0.07
    ÙĨع
    -0.07
    ric
    -0.06
    oss
    -0.06
     Keller
    -0.06
    POSITIVE LOGITS
    èĩ³
    0.07
    ÏĨο
    0.07
    æŶèĩ³
    0.06
    ClassLoader
    0.06
    abora
    0.06
    æĪªæŃ¢åĪ°
    0.06
    arder
    0.06
    éħ·
    0.06
    ű
    0.06
    garten
    0.06
    Activations Density 0.371%

    No Known Activations