© 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. 57291
    Prev
    Next
    INDEX
    Explanations

    months or years

    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
     midway
    -0.07
    è·µ
    -0.06
     instant
    -0.06
    æĪIJçĨŁ
    -0.06
    ä¸ŃæľŁ
    -0.06
    awning
    -0.06
    è½½
    -0.06
    åįĬæĪIJåĵģ
    -0.06
     ongoing
    -0.06
    èĩ¼
    -0.06
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.14
    çĶļèĩ³
    0.14
    çĶļèĩ³æĺ¯
    0.14
     voire
    0.14
    çĶļèĩ³åı¯ä»¥
    0.13
    çĶļèĩ³äºİ
    0.13
    çĶļèĩ³è¿ĺæľī
    0.12
    çĶļèĩ³ä¼ļ
    0.12
    çĶļèĩ³æľīäºĽ
    0.12
     tháºŃm
    0.12
    Activations Density 0.135%

    No Known Activations