© 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. 49411
    Prev
    Next
    INDEX
    Explanations

    copying and cleaning machines

    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
     Jó
    -0.07
    åİī
    -0.07
    åĪ¨
    -0.07
    tha
    -0.06
    Accessor
    -0.06
    ARAM
    -0.06
    еÑĢна
    -0.06
     Jat
    -0.06
    éĺ
    -0.06
     nexus
    -0.06
    POSITIVE LOGITS
    _using
    0.09
    _via
    0.08
    ãģ«ãģĬãģĦãģ¦ãģ¯
    0.08
    éľĢè¦ģå°Ĩ
    0.08
     involving
    0.08
    -grade
    0.08
    orsch
    0.08
     using
    0.08
    æĺ¯åĪ©çĶ¨
    0.08
    è¿ĩç¨ĭä¸ŃçļĦ
    0.07
    Activations Density 0.290%

    No Known Activations