© 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. 38816
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptions

    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
    onne
    -0.06
    æĪijæĢķ
    -0.06
    Âł
    -0.06
    ax
    -0.06
    ias
    -0.06
    ar
    -0.06
    ç»Ĩ
    -0.06
     "
    -0.05
    èn
    -0.05
    çĶ
    -0.05
    POSITIVE LOGITS
    çŀ»
    0.08
    æľĶ
    0.08
    åĤ¢ä¼Ļ
    0.08
    zado
    0.08
    çݯå¢ĥå½±åĵį
    0.08
    _HIDDEN
    0.08
    æŃ»ä¸į
    0.08
    usah
    0.08
     outright
    0.08
    _CF
    0.08
    Activations Density 0.001%

    No Known Activations