© 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. 41598
    Prev
    Next
    INDEX
    Explanations

    numbers and examples

    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
    æĢ§
    -0.07
    err
    -0.06
    ìĦ¸
    -0.06
    ale
    -0.06
    å¯Ħ
    -0.06
    ÄįÃŃ
    -0.06
    æĢ§æł¼
    -0.06
    产
    -0.06
    æ¬ł
    -0.05
    berries
    -0.05
    POSITIVE LOGITS
    osso
    0.09
    chado
    0.08
    vista
    0.08
    æ³ĵ
    0.08
    wski
    0.08
    orsch
    0.07
     isp
    0.07
     menjan
    0.07
    ÑĢик
    0.07
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    0.07
    Activations Density 0.102%

    No Known Activations