© 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. 8522
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical terms

    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
    常è§ĦçļĦ
    -0.07
    äºĶèĬ±
    -0.07
    åľ¨äºĨä¸Ģèµ·
    -0.07
    дÑĢи
    -0.06
    é¢Ŀ
    -0.06
    çĶļèĩ³æĺ¯
    -0.06
    éĽ£åº¦
    -0.06
    UnderTest
    -0.06
    常è§Ħ
    -0.06
    ,)
    -0.06
    POSITIVE LOGITS
    æĹ¢çĦ¶å¦ĤæѤ
    0.08
    åĨįæ·»
    0.08
    atable
    0.07
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    0.07
    å¸ĤåľºåĪĨæŀIJ
    0.07
    èĭ¥éĿŀ
    0.07
    åģ¥åº·å¿«ä¹IJ
    0.07
    为åķ¥
    0.07
     forall
    0.07
    åįģä¸ĢäºĶ
    0.07
    Activations Density 0.171%

    No Known Activations