© 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. 30515
    Prev
    Next
    INDEX
    Explanations

    probability distributions

    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
    mdb
    -0.08
    é¢ĿçļĦ
    -0.07
    aven
    -0.07
    åIJĦ项è§Ħç«łåĪ¶åº¦
    -0.06
    lessness
    -0.06
    _operand
    -0.06
    åĨ»
    -0.06
    ÛĮدا
    -0.06
    主è¦ģä»İ
    -0.06
    å¤ĦçļĦ
    -0.06
    POSITIVE LOGITS
    erguson
    0.08
    รวม
    0.07
    /Web
    0.07
    ustra
    0.07
    пли
    0.07
    .plist
    0.07
    intai
    0.07
    -shaped
    0.07
    ofire
    0.07
     #(
    0.07
    Activations Density 0.001%

    No Known Activations