© 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. 63254
    Prev
    Next
    INDEX
    Explanations

    False or NO

    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
    lined
    -0.07
    仿
    -0.06
    ries
    -0.06
    athed
    -0.06
    ta
    -0.06
    ech
    -0.06
    åĴĮ被
    -0.06
     uniquely
    -0.06
     and
    -0.06
    -0.06
    POSITIVE LOGITS
    æİīçļĦ
    0.09
    é¦Ĩ
    0.08
    .dist
    0.08
    bol
    0.08
    íݸ
    0.08
    ulat
    0.08
    ertz
    0.08
    æĥ³ä½ł
    0.08
    館
    0.08
    æĪ²
    0.07
    Activations Density 0.001%

    No Known Activations