© 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. 12070
    Prev
    Next
    INDEX
    Explanations

    example input output code file link

    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
    å°Ĥ
    -0.08
    uyên
    -0.07
    éĩįéĩįçļĦ
    -0.07
    å¹Į
    -0.07
    å¦ĤåĪĿ
    -0.07
    å¹´åįĬ
    -0.07
    onia
    -0.07
    argin
    -0.07
     brag
    -0.07
     predominant
    -0.07
    POSITIVE LOGITS
    çĥĤ
    0.07
    eri
    0.07
    جد
    0.07
    æģ©æĸ¯
    0.07
    鼷çĶµ
    0.07
    uses
    0.06
    à¹Īà¸Ńย
    0.06
    adders
    0.06
    bdb
    0.06
    ä¹ĭä¸Ģæĺ¯
    0.06
    Activations Density 0.009%

    No Known Activations