© 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. 4275
    Prev
    Next
    INDEX
    Explanations

    wet conditions

    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
    åĵ½
    -0.09
    erce
    -0.09
    stell
    -0.09
    schirm
    -0.09
    acier
    -0.08
    .dispatchEvent
    -0.08
    ARGV
    -0.08
    bjerg
    -0.08
    اÛĮØ´
    -0.08
    zinho
    -0.08
    POSITIVE LOGITS
    æµĬ
    0.10
    è¾ĥéĩį
    0.07
    éĩįçļĦ
    0.07
    æ·«
    0.07
     muddy
    0.07
    æ¿¡
    0.07
    kdir
    0.06
    æ»
    0.06
     Boot
    0.06
    éħĴ
    0.06
    Activations Density 0.001%

    No Known Activations