© 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. 30902
    Prev
    Next
    INDEX
    Explanations

    Macron, Thief, Shake, learning

    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
     AIDS
    -0.11
    æĸĩéĿ©
    -0.10
    éĿŀåħ¸
    -0.10
     fax
    -0.09
     videot
    -0.09
     USSR
    -0.08
    åħ¬å®³
    -0.08
    ä¸ĭå²Ĺ
    -0.08
    .sourceforge
    -0.08
     Fax
    -0.07
    POSITIVE LOGITS
    ç®ĹåĬĽ
    0.13
     TikTok
    0.12
     hashtag
    0.12
    ç½ij红
    0.12
    常æĢģåĮĸ
    0.12
     emojis
    0.11
     emoji
    0.11
     Biden
    0.11
    æĸĩæĹħ
    0.11
     tweeted
    0.11
    Activations Density 3.254%

    No Known Activations