© 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. 22867
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to comparison

    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
    rick
    -0.09
    oro
    -0.07
    æĿ¥è¶Ĭ
    -0.07
    aring
    -0.07
    pez
    -0.07
    argo
    -0.07
    åħ»çļĦ
    -0.07
    ä»®
    -0.07
    peratur
    -0.07
    opyright
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.11
    ï¸ı
    0.08
    /=
    0.08
    Ø©
    0.08
    人
    0.08
    utto
    0.08
    pired
    0.08
    Ùģت
    0.07
    áŁĭ
    0.07
    entication
    0.07
    Activations Density 0.007%

    No Known Activations