© 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. 62906
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
     Pru
    -0.07
    igas
    -0.07
    wegs
    -0.07
    åĬłéķ¿
    -0.07
    éĶĤ离åŃIJ
    -0.07
    ÑĦелÑĮ
    -0.07
    ä¸įèĩ³
    -0.06
    allis
    -0.06
    :)
    -0.06
     Vern
    -0.06
    POSITIVE LOGITS
    CJK
    0.07
    æł¹æį®åĽ½å®¶
    0.07
    ondo
    0.07
    è§ģ人
    0.07
    ืà¹Īà¸Ńà¸Ļ
    0.07
    blink
    0.07
     performs
    0.07
    æĮīçħ§åĽ½å®¶
    0.06
     Jays
    0.06
     performances
    0.06
    Activations Density 0.069%

    No Known Activations