© 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. 33017
    Prev
    Next
    INDEX
    Explanations

    death, biblical, nirvana, eyegasm

    np_acts-logits-general · gemini-2.5-flash-lite

    words with intense or extreme connotations, particularly those describing something impressive, severe, or extraordinary.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     somew
    -0.08
    ä¸įéĤ£ä¹Ī
    -0.07
    upu
    -0.07
    ä¸įæĺ¯å¾Ī
    -0.07
    æ¬łä½³
    -0.07
    åħīèį£
    -0.07
    åľĨ梦
    -0.07
    bars
    -0.07
    è¾ĥ为
    -0.07
    gere
    -0.07
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.17
    èĪ¬åľ°
    0.17
    级åĪ«çļĦ
    0.16
    级çļĦ
    0.16
    级
    0.14
     تÙĤرÙĬب
    0.14
    èĪ¬
    0.13
    级åĪ«
    0.12
    -level
    0.12
    ç´ļãģ®
    0.11
    Activations Density 0.742%

    No Known Activations