© 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. 26745
    Prev
    Next
    INDEX
    Explanations

    SN or Sn followed by specific suffixes

    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
    er
    -0.11
    erne
    -0.10
    ality
    -0.09
    eres
    -0.08
    erge
    -0.08
    eric
    -0.08
    eren
    -0.07
    à§įà¦Ł
    -0.07
    mente
    -0.07
    cul
    -0.07
    POSITIVE LOGITS
    erring
    0.09
    stel
    0.08
    holm
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    esistenza
    0.08
    Ø©
    0.08
    ä¹ĭéķ¿
    0.08
    agem
    0.07
    oring
    0.07
    ção
    0.07
    Activations Density 0.031%

    No Known Activations