© 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. 61977
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    araan
    -0.09
    mér
    -0.08
    andin
    -0.08
    ierzch
    -0.08
    urit
    -0.08
    roje
    -0.08
    orage
    -0.08
    aska
    -0.08
    রà§ĩর
    -0.08
    ums
    -0.08
    POSITIVE LOGITS
    ↵↵
    0.16
     ↵↵
    0.15
    	↵↵
    0.11
         ↵↵
    0.11
      ↵↵
    0.11
                    ↵↵
    0.10
    č↵č↵
    0.10
           ↵↵
    0.10
                ↵↵
    0.10
     č↵č↵
    0.09
    Activations Density 1.153%

    No Known Activations