© 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. 25629
    Prev
    Next
    INDEX
    Explanations

    section delimiters or headers

    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
    ingle
    -0.08
     thứ
    -0.07
    quer
    -0.07
    ematic
    -0.07
    麽
    -0.07
    å£ŀ
    -0.07
    ç¯Ħ
    -0.07
     Haz
    -0.07
    quet
    -0.07
    lott
    -0.06
    POSITIVE LOGITS
    enom
    0.07
    enin
    0.07
    ়
    0.07
     saud
    0.07
    驻马
    0.07
    åĹ£
    0.07
    chado
    0.07
    åħ·åIJĪ
    0.06
    į
    0.06
    æ²
    0.06
    Activations Density 0.284%

    No Known Activations