© 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. 61742
    Prev
    Next
    INDEX
    Explanations

    filling electron shells

    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
    olland
    -0.08
    kunst
    -0.08
    arel
    -0.08
    âtre
    -0.08
    ernet
    -0.08
    -errors
    -0.08
    entina
    -0.08
    venue
    -0.07
    gress
    -0.07
    æĪ¿åľ°
    -0.07
    POSITIVE LOGITS
    _iterator
    0.07
    cta
    0.07
    balanced
    0.07
    æŃ£å¥½
    0.07
    è¦ģä¹Īæĺ¯
    0.06
     symmetric
    0.06
    ajor
    0.06
     protection
    0.06
    æķ´é½IJ
    0.06
    ufe
    0.06
    Activations Density 0.001%

    No Known Activations