© 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. 63468
    Prev
    Next
    INDEX
    Explanations

    control, restrain, tame, temper, contain

    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
    ually
    -0.08
    ä¸Ģè¶Ł
    -0.07
    Clickable
    -0.07
    adop
    -0.07
    à¹Ĥà¸Ľà¸£à¸Ķ
    -0.07
    /operator
    -0.07
    undry
    -0.07
    irkan
    -0.07
    insip
    -0.07
    olarity
    -0.07
    POSITIVE LOGITS
    ä½ıäºĨ
    0.16
    åĴĮè§ĦèĮĥ
    0.13
    /control
    0.13
    åĴĮæݧåĪ¶
    0.13
    å¾Ĺä½ı
    0.13
    ä¸įä½ıçļĦ
    0.12
    éģıåĪ¶
    0.12
    æݧåĪ¶
    0.11
     جÙħا
    0.11
    ä¸įä½ı
    0.11
    Activations Density 0.132%

    No Known Activations