© 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. 58332
    Prev
    Next
    INDEX
    Explanations

    law, relationship, suffix

    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
    ked
    -0.08
    驳
    -0.07
    osso
    -0.07
    رÙħ
    -0.07
    空çļĦ
    -0.07
    ingan
    -0.07
    é¦Ļç²¾
    -0.07
    оÑģÑĥ
    -0.07
    GMT
    -0.07
    ÃŃce
    -0.07
    POSITIVE LOGITS
    å®ļå¾ĭ
    0.09
     relationship
    0.08
    åħ³ç³»
    0.08
     relationships
    0.07
    éĩıåĬĽ
    0.07
    æļĤæŶ
    0.07
    çŁŃæľŁ
    0.07
    åħ³ç³»çļĦ
    0.07
     law
    0.07
     ÙĤÙĬد
    0.07
    Activations Density 0.005%

    No Known Activations