© 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. 23506
    Prev
    Next
    INDEX
    Explanations

    ortho/para chemical positions

    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
    preh
    -0.10
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.08
    scr
    -0.08
    engan
    -0.08
    å¤ł
    -0.08
    zelf
    -0.07
    /process
    -0.07
    ract
    -0.07
    ÙĪÙħا
    -0.07
     keren
    -0.07
    POSITIVE LOGITS
     symmetric
    0.07
    èĥ½åĬĽå¼º
    0.07
    èĢĮåİ»
    0.07
    ä¼ĺåħĪ
    0.07
     options
    0.07
    -ish
    0.07
    è¦ĥ
    0.06
    Agen
    0.06
    idget
    0.06
    éĢī项
    0.06
    Activations Density 0.001%

    No Known Activations