© 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. 26351
    Prev
    Next
    INDEX
    Explanations

    academic and scientific terms

    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
    quent
    -0.08
     ÙĪبÙĬÙĨ
    -0.08
    /rem
    -0.07
     Oli
    -0.07
    αÏģ
    -0.07
    "And
    -0.07
    èĩªè¾¾
    -0.07
    ths
    -0.07
    é¢ĺ为
    -0.06
    åı¯è´µ
    -0.06
    POSITIVE LOGITS
    ãĢģ
    0.15
     ãĢģ
    0.11
    ãĢįãĢģãĢĮ
    0.11
    ãĢģãĢģ
    0.11
    ãĢģãĢĮ
    0.09
    ?,?,
    0.09
    ?,?,?,?,
    0.09
    ãĢģãĢİ
    0.09
    ãĢģ“
    0.08
    ãĢįãĢĮ
    0.08
    Activations Density 0.231%

    No Known Activations