© 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. 22760
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    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
    æµ¦æ±Ł
    -0.07
    CompanyName
    -0.07
    OptionPane
    -0.07
    à¸Ŀ
    -0.07
    ikir
    -0.07
     ortop
    -0.07
    JsonValue
    -0.07
    ocale
    -0.06
    失败äºĨ
    -0.06
    è¦ģéĹ»
    -0.06
    POSITIVE LOGITS
     nonetheless
    0.07
    çİ°å°±
    0.07
    åĽłæŃ¤åľ¨
    0.07
    åĽłæѤ
    0.07
     undes
    0.07
    主è¦ģåĪĨ为
    0.06
    æľī幸
    0.06
    çİ°å°Ĩ
    0.06
    èĴIJ
    0.06
    åı¯ä»¥åĪĨ为
    0.06
    Activations Density 1.370%

    No Known Activations