© 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. 63729
    Prev
    Next
    INDEX
    Explanations

    designation, part, reason, member, type

    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
    arness
    -0.08
    rana
    -0.07
     Khang
    -0.07
    avig
    -0.07
    riff
    -0.07
    åĭĻ
    -0.07
    ủ
    -0.07
    /nav
    -0.07
    _foot
    -0.07
    顾åIJįæĢĿä¹ī
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įæĺ¯
    0.10
    ä½Ĩä¸įèĥ½
    0.10
    éĹ´æİ¥
    0.08
     ÙĦÙĥÙĨÙĩ
    0.08
    ä½Ĩä¸į
    0.08
    ,but
    0.07
     indirect
    0.07
     but
    0.07
    ä½ĨæľĢç»Ī
    0.07
    éf
    0.07
    Activations Density 0.003%

    No Known Activations