© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28829
    Prev
    Next
    INDEX
    Explanations

    Third-Way, Asian style, Chinese state

    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
    etch
    -0.07
    .intent
    -0.07
    ieee
    -0.07
    äºĪåijĬ
    -0.07
    æĮijéĢī
    -0.07
    æī«
    -0.06
    ogr
    -0.06
    åģ¥
    -0.06
    amme
    -0.06
    ambda
    -0.06
    POSITIVE LOGITS
    ä¸ŃåĽ½çī¹èī²
    0.10
     adaptation
    0.10
    åĽłåľ°åĪ¶å®ľ
    0.10
    æij¸ç´¢
    0.10
    åİŁåĪĽ
    0.10
    çĭ¬çī¹çļĦ
    0.10
    çĭ¬åĪĽ
    0.10
    æĸ¹æ³ķ论
    0.09
    éĢĤåIJĪèĩªå·±çļĦ
    0.09
    ç»ıéªĮçļĦ
    0.09
    Activations Density 0.006%

    No Known Activations