© 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. 3198
    Prev
    Next
    INDEX
    Explanations

    specific characters or short strings

    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
    çŃīåĬŁèĥ½
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    ej
    -0.07
    ä»Ģä¹ĪæĦıæĢĿ
    -0.07
    çľĭåIJijäºĨ
    -0.07
    çŃīå¤ļç§į
    -0.07
    arder
    -0.07
    agama
    -0.07
    λÏİ
    -0.07
    รม
    -0.07
    POSITIVE LOGITS
     itself
    0.09
    æľ¬èº«
    0.08
    ÑĬÑĤ
    0.08
    åijĹ
    0.07
    æľ¬èº«å°±æĺ¯
    0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.07
    å½ĵçĦ¶æĺ¯
    0.06
    สัà¸į
    0.06
    ony
    0.06
    lemen
    0.06
    Activations Density 0.217%

    No Known Activations