© 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. 51471
    Prev
    Next
    INDEX
    Explanations

    potassium, K+, channels, loss, leak

    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
    odon
    -0.07
    olat
    -0.07
    eby
    -0.07
    inata
    -0.07
    зма
    -0.07
    edly
    -0.07
    olata
    -0.07
    zik
    -0.07
    Ŀ
    -0.06
    nde
    -0.06
    POSITIVE LOGITS
    assium
    0.09
     jad
    0.08
    incinn
    0.08
    ois
    0.08
    à§Ģয়
    0.08
    entially
    0.07
    ieger
    0.07
    iloc
    0.07
    ocket
    0.07
    oj
    0.07
    Activations Density 0.025%

    No Known Activations