© 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. 11894
    Prev
    Next
    INDEX
    Explanations

    seventeenth century

    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
     actuellement
    -0.08
    åģļ为
    -0.08
    currently
    -0.08
     currently
    -0.07
    ozilla
    -0.07
    çİ°æľīçļĦ
    -0.07
     sortOrder
    -0.07
     actualmente
    -0.07
    çİ°æľī
    -0.07
    Currently
    -0.07
    POSITIVE LOGITS
     soon
    0.09
    å¾Īå¿«å°±
    0.08
    —and
    0.08
     بØŃÙĦÙĪÙĦ
    0.07
    æĸ°éĹ®é¢ĺ
    0.07
     Soon
    0.07
    æĹ©åľ¨
    0.07
    å¾Īå¿«
    0.07
    soon
    0.07
     mattered
    0.07
    Activations Density 0.535%

    No Known Activations