© 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. 2468
    Prev
    Next
    INDEX
    Explanations

    previous comments or questions

    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
    å¤ıæĻ®
    -0.07
    arton
    -0.06
    é£İéľľ
    -0.06
    å°ij
    -0.06
    aras
    -0.06
    空
    -0.06
    tons
    -0.06
    åijĬè¯īä½ł
    -0.06
    åľºä¸Ĭ
    -0.06
    åijĬè¯ī
    -0.06
    POSITIVE LOGITS
     earlier
    0.09
    ä¸įä¹ħåīį
    0.09
     previous
    0.08
    angga
    0.08
    previous
    0.08
    mentioned
    0.08
    kota
    0.08
    _previous
    0.08
     snippet
    0.08
    alih
    0.08
    Activations Density 0.059%

    No Known Activations