© 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. 44033
    Prev
    Next
    INDEX
    Explanations

    pairs or two of things

    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
    ä¸īç±»
    -0.09
    ERA
    -0.08
    ering
    -0.07
    èݱæĸ¯
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    éĨī
    -0.07
    zuk
    -0.07
    eka
    -0.07
    ÏĦαÏĤ
    -0.07
    eki
    -0.07
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.11
     individually
    0.10
     ê°ģê°ģ
    0.09
    åIJĦåħ·
    0.09
    äºĴ为
    0.08
    åIJĦèĩª
    0.08
    åĪĨåĪ«ä¸İ
    0.08
    ä¿©
    0.08
    åIJĦæľī
    0.07
    å§ĭç»Īä¿ĿæĮģ
    0.07
    Activations Density 0.060%

    No Known Activations