© 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. 47072
    Prev
    Next
    INDEX
    Explanations

    electronics and circuits

    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
     ÑĤел
    -0.08
    çī©è´¨
    -0.07
    LBL
    -0.07
    æĿĸ
    -0.07
     XXL
    -0.07
     geo
    -0.07
    GBK
    -0.07
    亲
    -0.07
    æ°´ä½ĵ
    -0.07
    isson
    -0.07
    POSITIVE LOGITS
     voltage
    0.13
     Voltage
    0.13
    çĶµåİĭ
    0.12
    åħĥåĻ¨ä»¶
    0.12
    Voltage
    0.12
    åĻ¨ä»¶
    0.12
     electrical
    0.12
     electronics
    0.11
     circuit
    0.11
     transistor
    0.11
    Activations Density 0.468%

    No Known Activations