© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29742
    Prev
    Next
    INDEX
    Explanations

    then, then

    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
    ovin
    -0.09
    tones
    -0.09
    #error
    -0.08
    apesh
    -0.07
    鼾
    -0.07
    æĺ¯ä¸ĢéŨ
    -0.07
    LEAN
    -0.07
    peater
    -0.07
    andalone
    -0.07
    astics
    -0.07
    POSITIVE LOGITS
     ÑĤогда
    0.08
    azio
    0.07
    åĪĻ
    0.07
     Тогда
    0.07
    å¹³
    0.07
     Then
    0.07
    Then
    0.07
     then
    0.07
    ãģĻãĤĭãģ¨
    0.07
    è¿ĻæŶ
    0.07
    Activations Density 0.016%

    No Known Activations