© 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. 41193
    Prev
    Next
    INDEX
    Explanations

    example, reference, case

    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»Ģä¹Īåij¢
    -0.09
    æĢİä¹ĪåĬŀåij¢
    -0.09
    ][$
    -0.08
    odos
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    ä½ķæĸ¹
    -0.08
    สะ
    -0.07
    åĵī
    -0.07
    licer
    -0.07
    ovah
    -0.07
    POSITIVE LOGITS
    æĥħåĨµè¯´æĺİ
    0.10
    说æĺİ
    0.09
    åħ·ä½ĵçļĦ
    0.08
    åħ·ä½ĵ
    0.08
     explain
    0.08
    为ä¾ĭ
    0.08
    åħ·ä½ĵåĪĨæŀIJ
    0.07
     поÑıÑģ
    0.07
    并ç»ĵåIJĪ
    0.07
     explains
    0.07
    Activations Density 0.012%

    No Known Activations