© 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. 16125
    Prev
    Next
    INDEX
    Explanations

    biological structures or organizational units

    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
    &oacute
    -0.07
    ÂŃs
    -0.06
    âĢķâĢķ
    -0.06
    äºĶé¢ľåħŃèī²çļĦ
    -0.06
    èĮĹ
    -0.06
    ÂŃ
    -0.06
    lm
    -0.05
    æĨ§
    -0.05
    æĴ°
    -0.05
    .timedelta
    -0.05
    POSITIVE LOGITS
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    0.08
    úi
    0.07
    åī¯å¸Ĥéķ¿
    0.07
    åIJijä»ĸ们
    0.07
    ebi
    0.07
    åıijå¸ĥä¼ļä¸Ĭ
    0.07
    æī«çłģåħ³æ³¨
    0.07
    atology
    0.07
    åľ¨åįĹ京
    0.07
    ä¸įçŁ¥éģĵ该
    0.07
    Activations Density 0.184%

    No Known Activations