© 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. 4226
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
    vsp
    -0.08
    夫
    -0.07
    krim
    -0.07
    夫çļĦ
    -0.07
    áĥIJáĥķ
    -0.06
    oppi
    -0.06
    çĪ±ä¸Ĭ
    -0.06
    åįİé¾Ļ
    -0.06
    éªij
    -0.06
    ired
    -0.06
    POSITIVE LOGITS
    ç¯ĩä¸Ģ
    0.08
    å¾Ĺåħ¶
    0.07
    æĬľãģį
    0.07
    èĥĮçĹĽ
    0.07
    hoven
    0.07
    så
    0.07
    iban
    0.07
    _DIRS
    0.07
    ä»Ģä¹Īåij¢
    0.07
    isco
    0.07
    Activations Density 0.181%

    No Known Activations