© 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. 18038
    Prev
    Next
    INDEX
    Explanations

    Tanga application ultr HTML Long Beach sample

    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
    è¡Ŀ
    -0.08
    ared
    -0.07
    ired
    -0.07
    导
    -0.07
    irut
    -0.07
    ahas
    -0.06
    æĢ»è£ģ
    -0.06
    vard
    -0.06
    elat
    -0.06
    ardin
    -0.06
    POSITIVE LOGITS
    èī¯
    0.07
    æļĩ
    0.07
    æĶ¶éĽĨçļĦ
    0.07
    éĥ¨åĴĮ
    0.07
    åĪ©çī©
    0.07
     besti
    0.07
     Fle
    0.07
    éĶĢåĶ®ä¸ļ绩
    0.07
    让åĪ«äºº
    0.07
    ìĿ´ê¸°ëıĦ
    0.07
    Activations Density 0.089%

    No Known Activations