© 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. 11723
    Prev
    Next
    INDEX
    Explanations

    order by, now be

    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
    (priority
    -0.08
    unku
    -0.07
    typeid
    -0.07
    ×ij×ķ
    -0.07
     ->
    -0.07
    ç±³äºļ
    -0.07
    ondo
    -0.07
    ault
    -0.07
    -vers
    -0.06
    kers
    -0.06
    POSITIVE LOGITS
     expects
    0.08
    æĽ´éĩįè¦ģ
    0.07
    æĽ´æ³¨éĩį
    0.07
    ä½łå°±æĺ¯
    0.07
    çĶ¨å°ı
    0.07
     implicitly
    0.07
    awang
    0.07
     Gelegenheit
    0.07
    ĥĿ
    0.07
    (/[
    0.07
    Activations Density 0.007%

    No Known Activations