© 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. 18943
    Prev
    Next
    INDEX
    Explanations

    new Scanner

    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
    ourt
    -0.08
    sworth
    -0.07
    .unshift
    -0.07
    /Runtime
    -0.07
    itung
    -0.07
     Caro
    -0.07
    .yang
    -0.07
    [$_
    -0.07
    addir
    -0.07
    .epam
    -0.07
    POSITIVE LOGITS
    èĻİ
    0.07
    æ·ĺ
    0.07
    祥
    0.06
    .Buffer
    0.06
    æµĵ
    0.06
    ätz
    0.06
     Homemade
    0.06
    ("
    0.06
    æ°¸
    0.06
    åĩĮ
    0.06
    Activations Density 0.024%

    No Known Activations