© 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. 24632
    Prev
    Next
    INDEX
    Explanations

    fluid measurement

    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
    iesel
    -0.07
    toral
    -0.07
    _fatal
    -0.07
    enstr
    -0.07
     Ruhr
    -0.07
    idon
    -0.07
    æ¯ķä¸ļçĶŁå°±ä¸ļ
    -0.07
    elev
    -0.07
    Unnamed
    -0.07
     Svil
    -0.07
    POSITIVE LOGITS
    çŃīä¼łç»Ł
    0.11
    ç®Ģåįķåľ°
    0.09
    ä¼łç»ŁçļĦ
    0.08
    æĻ®éĢļçļĦ
    0.07
    /simple
    0.07
    ç®Ģåįķ
    0.07
    ç®ĢåįķçļĦ
    0.07
     tradicion
    0.07
    çļĦä¼łç»Ł
    0.07
    åĺī
    0.07
    Activations Density 0.044%

    No Known Activations