© 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. 9344
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters `{ }`

    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
    åĪĽ
    -0.07
    äºĭä¸ļçļĦ
    -0.07
    oring
    -0.07
    kaw
    -0.06
     capitalized
    -0.06
    airs
    -0.06
    åı¯ä»¥ä½ľä¸º
    -0.06
    éĨĴäºĨ
    -0.06
    天河
    -0.06
    åIJijè®°èĢħ
    -0.06
    POSITIVE LOGITS
    ANH
    0.08
    berra
    0.07
    isters
    0.07
    ampler
    0.06
    uhe
    0.06
    âĺħâĺħ
    0.06
    ubb
    0.06
    使åĩº
    0.06
    jah
    0.06
    anh
    0.06
    Activations Density 0.071%

    No Known Activations