© 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. 40743
    Prev
    Next
    INDEX
    Explanations

    saving time and money

    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
    ardini
    -0.08
    æĮĻ
    -0.08
    anty
    -0.07
     sobald
    -0.07
    gaard
    -0.07
    acar
    -0.07
    åĨįèµ·
    -0.07
    наÑĩ
    -0.07
    转载æĪĸ
    -0.07
    ä¸Ģè·¯
    -0.07
    POSITIVE LOGITS
     time
    0.12
    time
    0.11
    /time
    0.11
     spent
    0.11
    åĴĮæŶéĹ´
    0.10
    æŶéĹ´åİ»
    0.10
    å®Ŀè´µçļĦ
    0.10
     вÑĢемени
    0.10
    æŶéĹ´åĴĮç²¾åĬĽ
    0.10
     TIME
    0.10
    Activations Density 0.141%

    No Known Activations