© 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. 30264
    Prev
    Next
    INDEX
    Explanations

    conviction for illegal acts

    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
    ÄIJT
    -0.08
    å¾Ĺä½ı
    -0.08
    ðŁĺī
    -0.08
    obet
    -0.08
    æľĪä¸Ĭ
    -0.08
    elsea
    -0.08
    rhs
    -0.08
    æ¸ĭ
    -0.08
    éļıçĿĢæŶéĹ´çļĦ
    -0.08
    esson
    -0.07
    POSITIVE LOGITS
    æī°ä¹±
    0.09
    åĽ½å®¶æľºåħ³
    0.08
    æĺİçŁ¥
    0.07
    ä»ĸ人
    0.07
    çīŁ
    0.07
    ä¸İä»ĸ人
    0.07
     disrupt
    0.07
     Alter
    0.07
    妨害
    0.06
    第ä¸Ģ款
    0.06
    Activations Density 0.041%

    No Known Activations