© 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. 26610
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    aldo
    -0.06
    åİŁå§ĭçļĦ
    -0.06
    -bearing
    -0.06
    ä¸Ģæ°Ķ
    -0.06
    ä½ĵå¤ĸ
    -0.06
    éļĶå¤ľ
    -0.06
    ä¸įåıĤåĬł
    -0.06
    Ñĸб
    -0.06
    åģ¥åº·çĬ¶åĨµ
    -0.05
    èĩªæŁ¥
    -0.05
    POSITIVE LOGITS
    éĢĹçķĻ
    0.09
     angekommen
    0.09
    éĻĮçĶŁçļĦ
    0.09
    éĻĮçĶŁ
    0.09
    è¿Ļè¾¹çļĦ
    0.09
     ortam
    0.09
    eming
    0.08
    è¿ĻéĩĮæľī
    0.08
    æ°´åľŁ
    0.08
    ãģ§ãģ®
    0.08
    Activations Density 0.467%

    No Known Activations