© 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. 64830
    Prev
    Next
    INDEX
    Explanations

    capital expenditure depreciation equipment assets

    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
     máºŃt
    -0.07
    laus
    -0.07
    åįĥ家
    -0.07
    beck
    -0.07
    ople
    -0.07
    éĺ²ä¼ª
    -0.07
    æĪIJ交éĩı
    -0.07
    éĢŁéĢĴ
    -0.07
    人ä¸İ人ä¹ĭéĹ´
    -0.07
    lius
    -0.07
    POSITIVE LOGITS
    æĬĺæŧ
    0.15
     depreci
    0.14
     depreciation
    0.12
    åĽºå®ļèµĦ产
    0.11
    èĢIJçĶ¨
    0.11
     amort
    0.10
    使çĶ¨å¹´éĻIJ
    0.10
     амоÑĢÑĤи
    0.09
     equipment
    0.09
    è´Ńç½®
    0.09
    Activations Density 0.017%

    No Known Activations