© 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. 29950
    Prev
    Next
    INDEX
    Explanations

    uncertainty or seeking confirmation

    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
    undu
    -0.07
    æĪIJåĬŁåIJİåį³åı¯
    -0.07
    éľĢè¦ģ注æĦıçļĦæĺ¯
    -0.06
    zcz
    -0.06
    å°±èĥ½å¤Ł
    -0.06
    次åºı
    -0.06
    è¦ģ注æĦıçļĦæĺ¯
    -0.06
    éŨ
    -0.06
    اع
    -0.06
    é¦ĸåıij
    -0.06
    POSITIVE LOGITS
     consult
    0.11
    consult
    0.10
    åĴ¨è¯¢
    0.10
    请æķĻ
    0.08
     consulted
    0.08
    æŁ¥éĺħ
    0.08
    请åĴ¨è¯¢
    0.08
     Consult
    0.08
     consultar
    0.08
     consultations
    0.08
    Activations Density 0.003%

    No Known Activations