© 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. 22417
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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
    å¤ļå°ij
    -0.08
    oir
    -0.07
    derland
    -0.07
     AVG
    -0.07
    VG
    -0.06
    asakan
    -0.06
     applic
    -0.06
    applic
    -0.06
    ä¹Łä¸įå¤ļ
    -0.06
    keh
    -0.06
    POSITIVE LOGITS
    大äºİ
    0.17
    å°ıäºİ
    0.14
    é«ĺäºİ
    0.13
    ä½İäºİ
    0.13
    è¶ħè¿ĩ
    0.11
     >
    0.11
     surpass
    0.10
    æ¯Ķä½ł
    0.10
    è¶ħè¿ĩäºĨ
    0.10
    ä¼ĺäºİ
    0.09
    Activations Density 0.069%

    No Known Activations