© 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. 63626
    Prev
    Next
    INDEX
    Explanations

    Happy New Year, Day, Birthday

    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
    大ä½ĵ
    -0.08
    eking
    -0.07
    elio
    -0.07
    éĩįéĩį
    -0.07
    ä½Ĩæĺ¯åĽłä¸º
    -0.07
    /*/
    -0.07
    æ²
    -0.07
     Doming
    -0.07
    .Desc
    -0.07
    ļ
    -0.06
    POSITIVE LOGITS
    ias
    0.08
     indeed
    0.08
     âľĶ
    0.07
    ühl
    0.07
     confirms
    0.07
    igur
    0.07
    ä¸įèµ·æĿ¥
    0.07
    ths
    0.06
    ç¡®å®ŀæĺ¯
    0.06
    abad
    0.06
    Activations Density 0.003%

    No Known Activations