© 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. 32091
    Prev
    Next
    INDEX
    Explanations

    Logan fan

    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
    éĢĤçĶ¨ç®Ģæĺĵç¨ĭåºı
    -0.08
    åĭ¤
    -0.07
    WISE
    -0.07
    Leaks
    -0.07
    æ´»
    -0.06
    çļĦç¾İæĻ¯
    -0.06
    çĭĻ
    -0.06
     gier
    -0.06
    urnished
    -0.06
    åIJ¾
    -0.06
    POSITIVE LOGITS
    ãģĤãĤĮ
    0.07
    ubbo
    0.07
    ähr
    0.07
    ÅĤosi
    0.07
    änn
    0.07
    kken
    0.06
    ÅŁk
    0.06
    天边
    0.06
    aira
    0.06
    ight
    0.06
    Activations Density 0.575%

    No Known Activations