© 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. 2051
    Prev
    Next
    INDEX
    Explanations

    legal status of entities

    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
     Rubio
    -0.09
    天价
    -0.09
     Caro
    -0.08
    ä¹ħä¹ĭ
    -0.08
    ÏĪη
    -0.08
    è¿Ļä¸ĢéĹ®é¢ĺ
    -0.08
    åħĭéļ¾
    -0.08
    è¿Ļ对
    -0.07
    cheap
    -0.07
    GRAM
    -0.07
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.13
    缴æİ¥æĪĸéĹ´æİ¥
    0.12
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.11
    以任ä½ķ
    0.11
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.11
    ä»»ä½ķå½¢å¼ıçļĦ
    0.11
     reasonably
    0.09
     âī¥
    0.09
    æĪĸ以ä¸Ĭ
    0.09
    any
    0.09
    Activations Density 0.279%

    No Known Activations