© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13365
    Prev
    Next
    INDEX
    Explanations

    sections, divisions, compartments

    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
    anton
    -0.08
     enk
    -0.07
    å®ļçĤ¹
    -0.07
    æĿ¥èĩª
    -0.06
    泡水
    -0.06
    inox
    -0.06
    lific
    -0.06
    راÙģÙĬ
    -0.06
    群ä½ĵ
    -0.06
     Benn
    -0.06
    POSITIVE LOGITS
     separate
    0.09
     seperate
    0.09
    ,:,:
    0.08
     PRINCI
    0.08
    åIJįåī¯
    0.08
     divisions
    0.08
     populated
    0.08
     compartments
    0.08
     separately
    0.08
    ä¸ĵéĹ¨ä¸º
    0.08
    Activations Density 0.348%

    No Known Activations