© 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. 15988
    Prev
    Next
    INDEX
    Explanations

    eyes closed or opening

    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
    _DL
    -0.08
     redund
    -0.07
    çĪ¬ä¸Ĭ
    -0.07
    çļĦç¬ij声
    -0.07
    ouser
    -0.07
    oulos
    -0.07
    å¼ĤçļĦ
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    æĸ°åŀĭçļĦ
    -0.07
    zilla
    -0.07
    POSITIVE LOGITS
     Shut
    0.08
    à¸ļัà¸ĩ
    0.08
    æİ©
    0.07
    ä¸Ģå¿ĥ
    0.07
    phalt
    0.07
     lest
    0.07
    ä¸įçľĭ
    0.07
    åŁ¹åħ»
    0.07
     shutting
    0.07
     scrim
    0.07
    Activations Density 0.036%

    No Known Activations