© 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. 56937
    Prev
    Next
    INDEX
    Explanations

    scientific methods and results

    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
    å¤įåĪ¶æĪĸ
    -0.08
    æīį好
    -0.08
    è¦ģä¹Īæĺ¯
    -0.07
    æīįè¡Į
    -0.07
    æīĢè°ĵ
    -0.07
    ouis
    -0.07
    (and
    -0.07
    å°±æĺ¯äºĨ
    -0.07
    å¦ĤçĶ»
    -0.07
    è¿ĪåIJij
    -0.07
    POSITIVE LOGITS
    å¾ĹåĪ°äºĨ
    0.08
    åħ·æľīä¸Ģå®ļçļĦ
    0.08
    éļıçĿĢæŶéĹ´çļĦ
    0.08
    åıĬåIJĦ
    0.08
    åħ·æľīè¾ĥ强çļĦ
    0.07
    èĥ½å¤Łå¾ĹåĪ°
    0.07
    ä½Ĩæĺ¯çĶ±äºİ
    0.07
     Literature
    0.07
    对åħ¶è¿Ľè¡Į
    0.07
    åŁºéĩijé¡¹çĽ®
    0.07
    Activations Density 0.217%

    No Known Activations