© 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. 46877
    Prev
    Next
    INDEX
    Explanations

    code examples, method names, class definitions

    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
    oyer
    -0.07
     prop
    -0.07
    prop
    -0.07
    ţi
    -0.07
    æĥķ
    -0.06
    Prop
    -0.06
    æ¾
    -0.06
    ãĤ¸ãĤ§ãĥĥãĥĪ
    -0.06
    åij¨å²ģ以ä¸Ĭ
    -0.06
     magn
    -0.06
    POSITIVE LOGITS
    #index
    0.07
    #echo
    0.07
    dene
    0.07
    tern
    0.07
    å°±æĺ¯äºĨ
    0.07
    èĭ¦çļĦ
    0.07
    azos
    0.07
    ancode
    0.07
    åı£éķĩ
    0.07
    arat
    0.07
    Activations Density 0.011%

    No Known Activations