© 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. 20113
    Prev
    Next
    INDEX
    Explanations

    past tense verbs followed by research actions

    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
    ngu
    -0.08
    çļĦä¸Ģå¹´éĩĮ
    -0.08
     thing
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    ller
    -0.07
    å¼¥åĭĴ
    -0.07
     längst
    -0.07
     {}:
    -0.07
    landa
    -0.07
     punya
    -0.07
    POSITIVE LOGITS
     accordingly
    0.09
    iten
    0.07
    äºĪ以
    0.07
    å¦Ĥæŀľä¸įèĥ½
    0.07
    ç¡®å®ļ为
    0.07
    åħ¨éĿ¢
    0.06
     further
    0.06
    å±ķæľĽ
    0.06
    综åIJĪåĪĨæŀIJ
    0.06
    _STANDARD
    0.06
    Activations Density 0.669%

    No Known Activations