© 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. 19209
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions

    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
    åı¯èĥ½ä¼ļ对
    -0.08
    itz
    -0.07
    çīĪçļĦ
    -0.07
    代表çĿĢ
    -0.07
    éĤ£ä¹ĪæĪij们
    -0.07
    çļĦåħ·ä½ĵæĥħåĨµ
    -0.07
    æīĢèĥ½
    -0.07
    æĪij们èĥ½å¤Ł
    -0.07
    éľĢè¦ģ注æĦıçļĦæĺ¯
    -0.07
    å¾Ģå¾Ģä¼ļ
    -0.07
    POSITIVE LOGITS
    oton
    0.08
    kori
    0.08
    åIJĮä¸Ĭ
    0.07
    妥妥
    0.07
    ãĥ¼ãĤº
    0.07
    undra
    0.07
    erva
    0.07
    warts
    0.07
     YES
    0.07
    YES
    0.07
    Activations Density 0.001%

    No Known Activations