© 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. 13601
    Prev
    Next
    INDEX
    Explanations

    conjunctions or alternatives

    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
     má»įi
    -0.07
     دÙĦ
    -0.07
    hia
    -0.07
    éĻ¤äºĨ
    -0.07
    åĴĮ社ä¼ļåıijå±ķ
    -0.07
    åį¡åĴĮ
    -0.07
    spro
    -0.07
    åĴĮæľįåĬ¡
    -0.07
    rollers
    -0.07
    .getComponent
    -0.06
    POSITIVE LOGITS
    æĢ§ä»¥åıĬ
    0.09
     sowie
    0.09
     ebenso
    0.08
     vice
    0.08
    以åıĬ
    0.08
    以åıĬ对
    0.08
     oppure
    0.08
    以åıĬåľ¨
    0.07
    èĢħä¸İ
    0.07
     versus
    0.07
    Activations Density 0.565%

    No Known Activations