© 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. 43613
    Prev
    Next
    INDEX
    Explanations

    hole

    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
    ally
    -0.09
    à¸ģารà¸ĵà¹Į
    -0.09
    uten
    -0.08
    ently
    -0.08
     halnya
    -0.08
    ontaine
    -0.08
    äºİå¿ĥ
    -0.07
    igel
    -0.07
    ä»½å·¥ä½ľ
    -0.07
    yk
    -0.07
    POSITIVE LOGITS
    er
    0.11
    æ´ŀ
    0.09
    indsight
    0.09
    -hole
    0.08
    hole
    0.08
    sterol
    0.08
    å¾ij
    0.08
    ÙĦ
    0.07
    ight
    0.07
    Ī
    0.07
    Activations Density 0.025%

    No Known Activations