© 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. 27961
    Prev
    Next
    INDEX
    Explanations

    act, control, or treatment

    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
     undermin
    -0.08
    çİ°æľīæĬĢæľ¯
    -0.08
    acente
    -0.08
    è¦ģç»ı常
    -0.08
    Opened
    -0.08
    kte
    -0.08
    åħĪåĪ°
    -0.08
    ãģĺãĤģ
    -0.07
    urnished
    -0.07
    ç¦ıåħĭæĸ¯
    -0.07
    POSITIVE LOGITS
     accordingly
    0.11
    æį®æѤ
    0.11
    缸åºĶ
    0.09
    è¡ĮåĬ¨ä¸Ĭ
    0.08
     based
    0.08
    缸åºĶçļĦ
    0.08
     Based
    0.07
     remed
    0.07
    ä»ĺ诸
    0.07
    ents
    0.07
    Activations Density 0.458%

    No Known Activations