© 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. 57431
    Prev
    Next
    INDEX
    Explanations

    liquid, solid, or gaseous states

    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
    icali
    -0.08
    ä¼¼æĺ¯
    -0.08
    大æĦı
    -0.08
    ær
    -0.08
    inado
    -0.08
    rada
    -0.07
    ainter
    -0.07
    nowledge
    -0.07
    æ°´å¹³çļĦæıIJé«ĺ
    -0.07
    adak
    -0.07
    POSITIVE LOGITS
    常温
    0.10
    åĽºä½ĵ
    0.08
    æĢ§çĬ¶
    0.08
    液æĢģ
    0.08
    åĤ¨åŃĺ
    0.08
     readily
    0.08
    åĽºæĢģ
    0.08
    .Properties
    0.07
    /octet
    0.07
     Properties
    0.07
    Activations Density 0.018%

    No Known Activations