© 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. 24300
    Prev
    Next
    INDEX
    Explanations

    unique together, stand, carbohydrate, ratio, heptathlon

    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
    aranya
    -0.08
    huizen
    -0.08
    Ø´ÙĨ
    -0.08
    DeltaTime
    -0.08
    ={({
    -0.08
    arra
    -0.07
    .atom
    -0.07
    оÑĤÑĢе
    -0.07
    ÑĤÑı
    -0.07
    CTYPE
    -0.07
    POSITIVE LOGITS
    æĹłè®ºå¦Ĥä½ķ
    0.08
    å¿ħãģļ
    0.07
    è¨Ģä¹ĭ
    0.06
    niec
    0.06
    çļĦç¾İ好
    0.06
    ernes
    0.06
    人æ°ij代表大ä¼ļ常åĬ¡å§Ķåijĺä¼ļ
    0.06
    常ãģ«
    0.06
     ALWAYS
    0.06
    åį´å§ĭç»Ī
    0.06
    Activations Density 0.002%

    No Known Activations