© 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. 63850
    Prev
    Next
    INDEX
    Explanations

    signs and signals

    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
     strate
    -0.08
    .skip
    -0.07
    åĪĴåĪĨ为
    -0.07
    relude
    -0.07
     partition
    -0.07
    agi
    -0.07
     Jard
    -0.07
    cop
    -0.07
     comfortably
    -0.07
    æ¯Ķè¾ĥéĢĤåIJĪ
    -0.07
    POSITIVE LOGITS
    çĶ¨äºİ
    0.11
     universally
    0.09
     conventions
    0.09
    çĶ¨æĿ¥
    0.08
    è¯ĨåĪ«
    0.08
     internationally
    0.08
     symbols
    0.08
    设计è§ĦèĮĥ
    0.08
     codes
    0.08
     conveying
    0.08
    Activations Density 0.018%

    No Known Activations