© 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. 7910
    Prev
    Next
    INDEX
    Explanations

    both sides or ends

    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
    ä¹ĭç±»çļĦ
    -0.06
    lya
    -0.06
    ä¸İåĪĨæŀIJ
    -0.06
    们éĥ½
    -0.06
     versus
    -0.06
     ساÛĮر
    -0.06
     whereas
    -0.06
    ift
    -0.06
    åĩ°
    -0.06
    urator
    -0.06
    POSITIVE LOGITS
     hinweg
    0.09
     equally
    0.08
    éĹ´çļĦ
    0.08
    ä½Ĩ以
    0.08
    éĸĵçļĦ
    0.08
     alike
    0.08
    俨
    0.07
    룡
    0.07
    ãģ¿ãģ®
    0.07
    igator
    0.07
    Activations Density 0.104%

    No Known Activations