© 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. 12738
    Prev
    Next
    INDEX
    Explanations

    was followed by a noun or infinitive verb

    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
    åı°ä¸ĭ
    -0.07
     years
    -0.07
    ä¸ĢåĪĢ
    -0.07
    åľ¨çĶŁæ´»ä¸Ń
    -0.06
     invading
    -0.06
    P
    -0.06
    azed
    -0.06
    (
    -0.06
    cest
    -0.06
     annually
    -0.06
    POSITIVE LOGITS
    èµ·è§ģ
    0.09
    èĢ½æIJģ
    0.09
    Cls
    0.09
    å®īæİĴ好
    0.08
    两ä¸į误
    0.08
    çĹº
    0.08
    å¿ħçľĭ
    0.08
    HeaderText
    0.08
     discretion
    0.08
    SCRI
    0.08
    Activations Density 0.282%

    No Known Activations