© 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. 19565
    Prev
    Next
    INDEX
    Explanations

    unused materials or byproducts

    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
     shorthand
    -0.07
    rud
    -0.07
    ointed
    -0.07
    为äºĨä¿Ŀè¯ģ
    -0.07
    为äºĨæĸ¹ä¾¿
    -0.07
    asc
    -0.06
    为äºĨç¡®ä¿Ŀ
    -0.06
    æĸ¹æīį
    -0.06
    åİŁåıijæĢ§
    -0.06
    idy
    -0.06
    POSITIVE LOGITS
    éĹ²ç½®
    0.16
    åħħåĪĨåĪ©çĶ¨
    0.15
    åĨįåĪ©çĶ¨
    0.14
    åĴĮåĪ©çĶ¨
    0.13
    åĪ©çĶ¨
    0.13
     unused
    0.13
    åĪ©çĶ¨çİĩ
    0.13
     aproveit
    0.13
    Util
    0.12
    åIJĪçIJĨåĪ©çĶ¨
    0.12
    Activations Density 0.253%

    No Known Activations