© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    institutional structures

    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
    çļĦå°ıæīĭ
    -0.07
     slightly
    -0.07
    bies
    -0.07
    å¾Ĺå¿ĥ
    -0.06
    ä¸Ģæĺ¯è¦ģ
    -0.06
    paragus
    -0.06
    Ñĩко
    -0.06
    æĥ³å¾ĹåĪ°
    -0.06
    éĿĴåħīçľ¼
    -0.06
    ehme
    -0.06
    POSITIVE LOGITS
    aval
    0.08
    etwork
    0.08
    æĻ®éģį
    0.07
    éļıå¤Ħåı¯è§ģ
    0.07
     nationwide
    0.07
    kos
    0.07
    anz
    0.07
    æįIJ
    0.07
     Massive
    0.07
    大è§Ħ模
    0.07
    Activations Density 1.652%

    No Known Activations