© 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. 10654
    Prev
    Next
    INDEX
    Explanations

    `C`, `M` followed by digits

    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
    åĹ£
    -0.08
    æİĢ
    -0.08
    hei
    -0.07
    ommage
    -0.07
    å¹
    -0.07
    å¾Ĭ
    -0.07
     sertif
    -0.07
    หย
    -0.07
    anca
    -0.07
    quil
    -0.07
    POSITIVE LOGITS
    亡
    0.07
    æĭĽ
    0.06
     abw
    0.06
    åįģäºĮå¹´
    0.06
    odus
    0.06
    æ¯Ľè¡£
    0.06
    ä¸Ĭä¸ĭ
    0.06
    agues
    0.06
    ."\
    0.06
     ove
    0.06
    Activations Density 0.028%

    No Known Activations