© 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. 60606
    Prev
    Next
    INDEX
    Explanations

    complementary, opposite, inverse, linked, pair

    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
    å¤ļæĸ¹
    -0.07
    主ä½ĵçļĦ
    -0.07
     unexpectedly
    -0.07
    DS
    -0.07
    ãĤµãĥªãĥ¼
    -0.07
    äºijéĽĨ
    -0.06
    éģĵæĿ¥
    -0.06
     Falling
    -0.06
    _COMPILE
    -0.06
    åĽĽæĿ¡
    -0.06
    POSITIVE LOGITS
    äºĴ为
    0.19
    äºĴè¡¥
    0.15
     relationship
    0.15
    å½¼æѤ
    0.15
    çļĦåħ³ç³»
    0.14
    åħ³ç³»
    0.14
    缸äºĴ
    0.14
     saling
    0.14
     relationships
    0.14
     Relationship
    0.13
    Activations Density 0.051%

    No Known Activations