© 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. 48862
    Prev
    Next
    INDEX
    Explanations

    what does it mean

    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
    ardin
    -0.10
     تعÙĦ
    -0.07
    èĮ¬
    -0.07
    occhi
    -0.07
    olina
    -0.07
    .mac
    -0.07
    ç¼ĸè¾ijäºİ
    -0.07
    δεί
    -0.07
    羣æĥ³
    -0.07
    atro
    -0.07
    POSITIVE LOGITS
    ken
    0.06
    ãĢĮ
    0.06
    åĨķ
    0.06
    çķĻ
    0.06
    ”ï¼Į
    0.06
    iber
    0.06
    MBER
    0.06
    íĥĿ
    0.06
    iete
    0.06
    avor
    0.06
    Activations Density 0.002%

    No Known Activations