© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30555
    Prev
    Next
    INDEX
    Explanations

    Judge, derivative, -share

    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
    ouv
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    æīĢè°ĵçļĦ
    -0.07
    ç¼¥
    -0.07
    æļĹ示
    -0.07
    çļĦæīĢæľī
    -0.07
     generic
    -0.07
     somehow
    -0.07
    å¥Ī
    -0.07
    ivr
    -0.07
    POSITIVE LOGITS
    å·²åĪ°
    0.07
    å·²æĪIJåĬŁ
    0.07
     replic
    0.06
    å·²æĪIJ为
    0.06
    æĮīè¦ģæ±Ĥ
    0.06
    itage
    0.06
    è¿Ļæĺ¯å¯¹
    0.06
    åıĬè¦ģæ±Ĥ
    0.06
    idler
    0.06
    æ¡Īä¾ĭåĪĨæŀIJ
    0.06
    Activations Density 0.009%

    No Known Activations