© 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. 31053
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    toff
    -0.08
    rana
    -0.08
     sahab
    -0.08
    æŦ
    -0.08
    ulled
    -0.08
    /oct
    -0.07
    ÛĮزÛĮ
    -0.07
    SizeMode
    -0.07
    {name
    -0.07
    axter
    -0.07
    POSITIVE LOGITS
    isas
    0.06
    otta
    0.06
    als
    0.06
     P
    0.06
    0.06
    ней
    0.06
     forn
    0.06
    chie
    0.06
    ati
    0.06
    主è¦ģ为
    0.06
    Activations Density 0.002%

    No Known Activations