© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46585
    Prev
    Next
    INDEX
    Explanations

    investigate deaths

    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
    åIJİèĢħ
    -0.06
    績
    -0.06
    åīįåĪĹ
    -0.06
    åIJĪä½ĵ
    -0.06
    æ©
    -0.06
     ()
    -0.06
    arana
    -0.06
    ÙĤÙī
    -0.06
    åħ¸
    -0.05
     hei
    -0.05
    POSITIVE LOGITS
    ahan
    0.10
    yek
    0.08
    å¸ĤæĶ¿åħ¬çĶ¨
    0.08
    мона
    0.08
    åı¯ä»¥åĪĨ为
    0.07
    .startTime
    0.07
    æĪIJèĢĥ
    0.07
    ytu
    0.07
    缴æİ¥æĪĸ
    0.07
     Binder
    0.07
    Activations Density 0.010%

    No Known Activations