© 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. 3003
    Prev
    Next
    INDEX
    Explanations

    Kincaid, 'Nole, below, CC.NET, Interface, lunar

    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
    çĥ¨
    -0.07
    leter
    -0.07
    æīĢè§ģ
    -0.07
    æĸ°åįİ
    -0.07
    íķĻ
    -0.06
    åİŁä»¶
    -0.06
     âĢİ
    -0.06
    Rgb
    -0.06
    eneg
    -0.06
    KHR
    -0.06
    POSITIVE LOGITS
    éĽģ
    0.07
    akarta
    0.07
    ursive
    0.07
    ovsky
    0.07
     chÃŃ
    0.06
    edik
    0.06
    quist
    0.06
    cta
    0.06
    .defaults
    0.06
    (fetch
    0.06
    Activations Density 0.007%

    No Known Activations