© 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. 28536
    Prev
    Next
    INDEX
    Explanations

    links to next or downstream

    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
    åĬŁåĭĭ
    -0.08
    é¦ĻçļĦ
    -0.08
    loge
    -0.08
    è¡ĢçļĦ
    -0.07
    人类社ä¼ļ
    -0.07
     pein
    -0.07
    zeh
    -0.07
    rego
    -0.07
    angeb
    -0.07
    .sum
    -0.07
    POSITIVE LOGITS
    roup
    0.07
    _preview
    0.07
    æ¯Ĺ
    0.07
     next
    0.07
    esco
    0.07
    lassian
    0.07
    efe
    0.07
    é²²
    0.07
    åĴĮæľªæĿ¥
    0.07
    ünft
    0.07
    Activations Density 0.010%

    No Known Activations