© 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. 56751
    Prev
    Next
    INDEX
    Explanations

    product offerings

    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
    è¦ģä¹Ī
    -0.08
     pair
    -0.08
    åŃĺ
    -0.07
    è¦ģä¹Īæĺ¯
    -0.07
    Pair
    -0.07
    olen
    -0.06
     Pair
    -0.06
    ãģĦãģļãĤĮ
    -0.06
    (pair
    -0.06
    _ALWAYS
    -0.06
    POSITIVE LOGITS
    åĮħåIJ«äºĨ
    0.14
     comprehensive
    0.14
    åĨħ容åĮħæĭ¬
    0.13
    åĨħ容丰å¯Į
    0.13
    åħ¨éĿ¢çļĦ
    0.13
    åĮħæĭ¬äºĨ
    0.13
    åħ¶ä¸ŃåĮħæĭ¬
    0.13
    綾åIJĪ
    0.12
    åħ¨éĿ¢
    0.12
    åºĶåĮħæĭ¬
    0.12
    Activations Density 1.280%

    No Known Activations