© 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. 30013
    Prev
    Next
    INDEX
    Explanations

    link or clickable element attributes

    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
    é¼İ
    -0.07
    éģģ
    -0.07
    æĨ¬
    -0.07
    åĿ
    -0.07
    Fair
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.06
    fair
    -0.06
    山顶
    -0.06
    toMatchSnapshot
    -0.06
     Fair
    -0.06
    POSITIVE LOGITS
     onclick
    0.10
    onclick
    0.10
    href
    0.09
     href
    0.09
     onClick
    0.09
     tabindex
    0.09
     clickable
    0.09
    .href
    0.08
    pointer
    0.08
    .onclick
    0.08
    Activations Density 0.235%

    No Known Activations