© 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. 1188
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions like "but"

    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
     reverse
    -0.07
    LOT
    -0.07
    çĤ¼
    -0.07
    åİī
    -0.06
    Reverse
    -0.06
     Reverse
    -0.06
    empl
    -0.06
     lot
    -0.06
    ón
    -0.06
    饱
    -0.06
    POSITIVE LOGITS
    çĦ¶èĢĮåľ¨
    0.09
    åľ¨å®ŀéĻħ
    0.08
    ä¸į计
    0.07
    å®ŀéĻħçļĦ
    0.07
    iji
    0.07
    æĺ¯åı¯
    0.07
    _async
    0.07
    è¡ĮåĬ¨ä¸Ĭ
    0.07
    æ¼ĶåĩºçļĦ
    0.07
    entar
    0.07
    Activations Density 0.018%

    No Known Activations