© 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. 46592
    Prev
    Next
    INDEX
    Explanations

    lower value items

    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
    æŦ
    -0.07
    aka
    -0.06
    åį³åľ¨
    -0.06
     lique
    -0.06
    å¤ĸåĽ½è¯ŃåѦéĻ¢
    -0.06
    elic
    -0.06
    èĩªä½ľ
    -0.06
    çĻ»ä¸Ĭ
    -0.06
    æ¯ıçıŃ
    -0.06
     northeastern
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.13
     magari
    0.12
    个æĪĸå¤ļ个
    0.12
    æĪĸèĢħåħ¶ä»ĸ
    0.12
    ãģĦãģŁãĤĬ
    0.11
    åĽ¾çīĩæĪĸ
    0.11
    æŁIJäºĽ
    0.11
    æĪĸåħ¶å®ĥ
    0.11
    æĪĸå¤ļ个
    0.11
    åıĪæĪĸèĢħ
    0.10
    Activations Density 0.019%

    No Known Activations