© 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. 15351
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation like hyphens and colons

    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
    opoulos
    -0.08
    éĵ²
    -0.08
    иж
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.07
    ä¸ĭåIJĮ
    -0.07
    .acc
    -0.07
    éħįæĸ¹
    -0.07
    æķĻèĤ²å·¥ä½ľèĢħ
    -0.07
    æĬĺç®Ĺ
    -0.07
    ãĥĪãĥł
    -0.07
    POSITIVE LOGITS
    ×ŀ×ķת
    0.08
    orida
    0.07
    åį°è±¡
    0.07
    omit
    0.07
    keen
    0.06
    rash
    0.06
    gary
    0.06
    é¡Į
    0.06
    ÑĢое
    0.06
    ood
    0.06
    Activations Density 0.019%

    No Known Activations