© 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. 4135
    Prev
    Next
    INDEX
    Explanations

    explicit, detailed, specific, emphasize

    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
     either
    -0.09
    .generated
    -0.08
     либо
    -0.08
     EITHER
    -0.08
    Either
    -0.08
    either
    -0.07
     DBNull
    -0.07
     ÙĪرد
    -0.07
     Either
    -0.07
    acus
    -0.07
    POSITIVE LOGITS
     explicitly
    0.14
     explicit
    0.13
    explicit
    0.12
    æĺİç¡®
    0.12
    Explicit
    0.11
     Explicit
    0.11
    强è°ĥäºĨ
    0.09
    强è°ĥ
    0.09
    æĺİç¡®çļĦ
    0.09
     emphasized
    0.09
    Activations Density 0.021%

    No Known Activations