© 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. 10530
    Prev
    Next
    INDEX
    Explanations

    anti-inflammatory drugs

    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
     Tanks
    -0.07
    tank
    -0.07
     Tank
    -0.07
    çĮ
    -0.07
    fq
    -0.07
    IER
    -0.07
    赦
    -0.07
    afb
    -0.07
     Tunnel
    -0.07
    صب
    -0.07
    POSITIVE LOGITS
    éķĩçĹĽ
    0.09
    æĬĹçĤİ
    0.09
    éłŃçĹĽ
    0.09
    éĢĢçĥ§
    0.09
    adol
    0.08
    头çĹĽ
    0.08
    æŃ¢çĹĽ
    0.08
    æ¶ĪçĤİ
    0.08
    çĸ¼çĹĽ
    0.08
    çĹ¹
    0.07
    Activations Density 0.067%

    No Known Activations