© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34165
    Prev
    Next
    INDEX
    Explanations

    past tense verbs or state descriptions

    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
     prior
    -0.08
    åIJĹ
    -0.07
    ±
    -0.07
    以åīį
    -0.07
    æĥľ
    -0.07
    å§ĭç»Ī
    -0.06
    Continue
    -0.06
    æıIJåīį
    -0.06
    äºİæѤ
    -0.06
    then
    -0.06
    POSITIVE LOGITS
     ÙĪÙĤبÙĦ
    0.11
     ÙĦØ£ÙĪÙĦ
    0.10
    æŃ£å¼ıå¼Ģå§ĭ
    0.09
    æľĢåIJİä¸Ģ次
    0.08
     оÑĩеÑĢедной
    0.08
    å°ĺåŁĥ
    0.08
    第ä¸Ģ个
    0.08
     оконÑĩаÑĤелÑĮно
    0.08
    第ä¸Ģ家
    0.08
    å·®ä¸įå¤ļ
    0.08
    Activations Density 0.434%

    No Known Activations