© 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. 16096
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and states

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

    words related to positive qualities or pleasant experiences, particularly those describing aesthetic, emotional, or atmospheric appeal.

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    æł¹æį®éľĢè¦ģ
    -0.06
    éĻ¤äºĨè¦ģ
    -0.06
    æŦ
    -0.06
    æĺ¯åħ·æľī
    -0.06
    -0.06
    æ²¾
    -0.06
    ,
    -0.06
    POSITIVE LOGITS
    hver
    0.10
    ussen
    0.09
    两ä¸į误
    0.09
    ÙĴرÙIJ
    0.09
    ä¹ĭå®Ŀ
    0.09
    0.09
    Qed
    0.08
    zcz
    0.08
    ammen
    0.08
    é£İ头
    0.08
    Activations Density 0.037%

    No Known Activations