© 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. 2064
    Prev
    Next
    INDEX
    Explanations

    gamma-aminobutyric acid (GABA)

    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
    eis
    -0.08
    vek
    -0.08
    chio
    -0.08
    ftp
    -0.07
    Ïĥμα
    -0.07
    åĨħèĨľ
    -0.07
    azo
    -0.06
    çīŁ
    -0.06
    quam
    -0.06
     vessel
    -0.06
    POSITIVE LOGITS
    å®īç¥ŀ
    0.09
    æĹłèĻij
    0.09
    å®īå®ļ
    0.08
     Paran
    0.08
     neurotrans
    0.08
    æŶä¸ĭ
    0.08
    .googlecode
    0.08
    äºĮè¿ŀ
    0.08
    å®ī
    0.08
    ç·ł
    0.08
    Activations Density 0.057%

    No Known Activations