© 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. 31183
    Prev
    Next
    INDEX
    Explanations

    test and example cases

    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
    庶
    -0.07
    AMS
    -0.07
    iev
    -0.07
    åIJĦçıŃ
    -0.06
    çķĮéĿ¢
    -0.06
    å°ıè®°èĢħ
    -0.06
    罪éŃģ
    -0.06
    éħ¸
    -0.06
    åĩī
    -0.06
    ueur
    -0.06
    POSITIVE LOGITS
     cas
    0.08
    çļĦä¸Ģ对
    0.07
     input
    0.07
    äºĭä¾ĭ
    0.07
    å±ķ示
    0.07
    ondre
    0.07
     Batch
    0.07
    /input
    0.07
    andır
    0.07
     pairs
    0.06
    Activations Density 0.014%

    No Known Activations