© 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. 17069
    Prev
    Next
    INDEX
    Explanations

    classes, portions, or remaining parts

    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
    åī§
    -0.07
     im
    -0.07
     effect
    -0.06
    çĤ¹å¤ļ
    -0.06
    æķĪæŀľ
    -0.06
    zugs
    -0.06
    æľīç¼ĺ
    -0.06
    çĮľä½łåĸľæ¬¢
    -0.06
    éĿ¢æĹł
    -0.06
    iales
    -0.06
    POSITIVE LOGITS
     restantes
    0.10
     Partition
    0.09
    åī©ä¸ĭçļĦ
    0.09
    åĪĴåĪĨ
    0.09
    åī©ä¸ĭ
    0.09
     restante
    0.09
     complementary
    0.09
    åĪĨåī²
    0.09
    remaining
    0.08
    Partition
    0.08
    Activations Density 0.055%

    No Known Activations