© 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. 17999
    Prev
    Next
    INDEX
    Explanations

    what to do

    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
    orean
    -0.07
    åıijçĶŁåľ¨
    -0.07
    Occurs
    -0.07
    TimeInterval
    -0.07
    å¼ĢåĬ¨
    -0.06
    mous
    -0.06
    åıijçĶŁåIJİ
    -0.06
     sini
    -0.06
    _SCL
    -0.06
    åĪ¹
    -0.06
    POSITIVE LOGITS
    builder
    0.07
    ouverte
    0.07
    åĴĮå¸Ĥ
    0.07
    amkan
    0.07
    bay
    0.07
    ugn
    0.07
    çŃīå¹³åı°
    0.07
    åĨħ容为
    0.06
    æ¹¾åĮº
    0.06
    å®īçIJª
    0.06
    Activations Density 1.251%

    No Known Activations