© 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. 55332
    Prev
    Next
    INDEX
    Explanations

    short or concise descriptions

    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
    alem
    -0.08
    ale
    -0.07
    ront
    -0.07
    غار
    -0.07
    å·¥ç¨ĭåѦéĻ¢
    -0.06
    ope
    -0.06
    ãģĨãĤĮ
    -0.06
    orio
    -0.06
    .binding
    -0.06
    sole
    -0.06
    POSITIVE LOGITS
     overview
    0.12
    æµĵ缩
    0.11
    overview
    0.11
     concise
    0.11
    ç²¾çĤ¼
    0.11
     brev
    0.10
    çªģåĩºéĩįçĤ¹
    0.10
     quick
    0.10
    æ¦Ĥæĭ¬
    0.10
     Ãľberblick
    0.10
    Activations Density 0.079%

    No Known Activations