© 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. 32984
    Prev
    Next
    INDEX
    Explanations

    prophylactic age

    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
    çĸ£
    -0.07
    adel
    -0.07
    æĥĭ
    -0.07
    å½¹
    -0.06
    ãģªãģķ
    -0.06
    ãģİãĤĬ
    -0.06
    zd
    -0.06
    åIJĮæĹ¶ä¹Łåı¯ä»¥
    -0.06
    çļĦ强大
    -0.06
    ì§ľ
    -0.06
    POSITIVE LOGITS
    åħ®
    0.11
    è¾Ľåĭ¤
    0.09
    iso
    0.07
    inique
    0.07
    åıªåĽł
    0.07
    енÑĮе
    0.07
     ÐŀÑģо
    0.07
    å½ĵä¸Ń
    0.07
    mination
    0.07
    梦éĩĮ
    0.07
    Activations Density 0.147%

    No Known Activations