© 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. 61550
    Prev
    Next
    INDEX
    Explanations

    list of countries

    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
    orna
    -0.07
     Fé
    -0.06
    åĽłä¸ºåıªæľī
    -0.06
    tren
    -0.06
    гÑĭ
    -0.06
    ä½Ĩæĺ¯çĶ±äºİ
    -0.06
    IFS
    -0.06
    æ¯Ķäºļ
    -0.05
     Paz
    -0.05
    ÙĬاÙĩ
    -0.05
    POSITIVE LOGITS
    å¾Īåı¯èĥ½
    0.08
    为äºĨæĸ¹ä¾¿
    0.08
    æľªå¿ħ
    0.08
     presumably
    0.08
    ä¸įä¸Ģå®ļ
    0.08
    说ä¸įå®ļ
    0.08
    æĥ³å®ļ
    0.08
    inee
    0.08
    æĪij们æĺ¯
    0.07
    ä¿
    0.07
    Activations Density 0.005%

    No Known Activations