© 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. 14221
    Prev
    Next
    INDEX
    Explanations

    court cases and documentation

    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
    ono
    -0.08
    æ²ĥæĸ¯
    -0.08
    ä»Ģä¹ĪçļĦ
    -0.07
    мÑı
    -0.06
    sted
    -0.06
    æĹ¥æĻĤ
    -0.06
    æŁĦ
    -0.06
    resents
    -0.06
    abase
    -0.06
     sez
    -0.06
    POSITIVE LOGITS
    anzo
    0.09
    cking
    0.08
    æĿİåĺī
    0.08
    ropa
    0.07
    ECK
    0.07
    ä¸Ģå¾ĭ
    0.07
    cks
    0.07
    arts
    0.07
    uret
    0.07
    ambul
    0.06
    Activations Density 0.040%

    No Known Activations