© 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. 29886
    Prev
    Next
    INDEX
    Explanations

    network communication

    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
    æĬ±
    -0.08
    å¡ŀ
    -0.07
    ibox
    -0.07
    æ¶īåıĬçīĪæĿĥ
    -0.07
     Lá»ĩ
    -0.07
    æĭ¶
    -0.07
    æĿł
    -0.07
    adium
    -0.07
    quartered
    -0.07
     angk
    -0.07
    POSITIVE LOGITS
    å¯¹ä½ł
    0.08
    对æĪij
    0.08
    æİ¥å¾ħ
    0.07
    pter
    0.07
    igny
    0.07
     recip
    0.07
     má»Ŀi
    0.07
    åįĴ
    0.07
    对æĪijæĿ¥è¯´
    0.07
     prov
    0.07
    Activations Density 0.279%

    No Known Activations