© 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. 31332
    Prev
    Next
    INDEX
    Explanations

    until

    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
    å½Ĵ宿
    -0.07
    ä¸Ģè¨Ģ
    -0.07
    æĸŃ
    -0.06
    çī§åľº
    -0.06
    á»ķ
    -0.06
    ady
    -0.06
    æŃī
    -0.06
    acor
    -0.06
    opot
    -0.06
     vux
    -0.06
    POSITIVE LOGITS
    缴åĪ°
    0.25
    until
    0.25
     until
    0.25
     initially
    0.23
     Until
    0.22
    Until
    0.21
    åĪĿæľŁ
    0.21
    æļĤæŶ
    0.21
    åĪĿæľŁçļĦ
    0.21
     temporarily
    0.21
    Activations Density 0.335%

    No Known Activations