© 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. 20373
    Prev
    Next
    INDEX
    Explanations

    INSTALL commands

    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
    ottes
    -0.09
    enburg
    -0.08
    cala
    -0.08
    äºķåĨĪ
    -0.07
    benh
    -0.07
     Monad
    -0.07
    otto
    -0.07
    otti
    -0.07
    otal
    -0.07
    ehm
    -0.07
    POSITIVE LOGITS
    acs
    0.08
    iner
    0.08
    resco
    0.07
    å°½äºĨ
    0.07
    RAD
    0.06
    grab
    0.06
    inated
    0.06
    รร
    0.06
    çĽ¸å¯¹åºĶçļĦ
    0.06
    ä¼Ļ
    0.06
    Activations Density 0.274%

    No Known Activations