© 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. 18253
    Prev
    Next
    INDEX
    Explanations

    books, albums, CDs

    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
    åıijçŁŃä¿¡
    -0.08
    ousel
    -0.08
    ainter
    -0.08
    Painter
    -0.08
    è¨ĺäºĭãĤĴ
    -0.07
    æīĢåѦçļĦ
    -0.07
    鼻åŃIJåł±
    -0.07
    æĤ£
    -0.07
    ç«¿
    -0.07
    åĽŀå¸ĸ
    -0.07
    POSITIVE LOGITS
    çķħéĶĢ
    0.11
    åĩºçīĪ
    0.11
     ISBN
    0.11
     editions
    0.10
    ISBN
    0.10
    æīī
    0.09
    éĹ®ä¸ĸ
    0.09
    è£ħ帧
    0.09
     edition
    0.09
    åıijè¡Į
    0.09
    Activations Density 0.751%

    No Known Activations