© 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. 47564
    Prev
    Next
    INDEX
    Explanations

    drug, toxin, cytokine, former medication

    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
     punc
    -0.06
    pio
    -0.06
    zzi
    -0.06
    สมา
    -0.06
     mies
    -0.06
    士
    -0.06
    rer
    -0.06
    ãĤªãĥ¼
    -0.06
    er
    -0.06
    arton
    -0.05
    POSITIVE LOGITS
     Ingy
    0.08
    .fromJson
    0.08
     [|
    0.08
    idge
    0.07
    addin
    0.07
    é¾Ļåĩ¤
    0.07
    å±ħæĺĵ
    0.07
    thought
    0.07
    lott
    0.07
    ç¯ĵ
    0.07
    Activations Density 0.590%

    No Known Activations