© 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. 10686
    Prev
    Next
    INDEX
    Explanations

    experimental study conditions

    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
    สà¸Ļิà¸Ĺ
    -0.09
    NESS
    -0.09
    ëģĶ
    -0.09
    innie
    -0.09
    avance
    -0.09
    ahari
    -0.09
    iliz
    -0.09
    ovy
    -0.08
    amax
    -0.08
    erd
    -0.08
    POSITIVE LOGITS
     nghiá»ĩm
    0.09
    neh
    0.08
    æĪIJè´¥
    0.07
    ically
    0.07
    atic
    0.07
     contrario
    0.07
    ì©
    0.06
    èİ«æµĭ
    0.06
    imonials
    0.06
    sWith
    0.06
    Activations Density 0.026%

    No Known Activations