© 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. 60518
    Prev
    Next
    INDEX
    Explanations

    compression codecs, comparison websites, catch block

    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
     Asc
    -0.06
    ©
    -0.06
    ("__
    -0.06
    æłĢ
    -0.06
    -api
    -0.05
    cede
    -0.05
    entanyl
    -0.05
    à¹īà¸Ńย
    -0.05
     API
    -0.05
    çIJµ
    -0.05
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.09
    ä¸ĭä¸Ģç«ł
    0.08
    adura
    0.07
     дÑĥÑĪ
    0.07
    ä¸Ģç«ł
    0.07
    å°½åľ¨
    0.07
    ä¸ĭä¸Ģç¯ĩ
    0.07
    akra
    0.07
    bart
    0.07
    issance
    0.07
    Activations Density 0.005%

    No Known Activations