© 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. 15133
    Prev
    Next
    INDEX
    Explanations

    producer or manager

    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
    æĻ®æĭī
    -0.07
    æĻı
    -0.07
    semblies
    -0.07
    ahasa
    -0.06
    æĶ¾çļĦ
    -0.06
     prad
    -0.06
    ahari
    -0.06
    eler
    -0.06
    пÑĢÑĥ
    -0.06
    ÑĢид
    -0.06
    POSITIVE LOGITS
    "@
    0.07
    zos
    0.07
    约车
    0.06
    êmes
    0.06
    umon
    0.06
    uya
    0.06
    UY
    0.06
    าวà¸Ļà¹Į
    0.06
    UN
    0.06
    å¸ĥæĸ¯
    0.06
    Activations Density 0.052%

    No Known Activations