© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30551
    Prev
    Next
    INDEX
    Explanations

    ABC superfamily, family, receptors, classify

    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
     Babe
    -0.06
    alap
    -0.06
    åIJĬ
    -0.06
    vo
    -0.06
    è´¨
    -0.05
    Kit
    -0.05
    st
    -0.05
    1
    -0.05
     surre
    -0.05
    æł¹æľ¬
    -0.05
    POSITIVE LOGITS
    家æĹıçļĦ
    0.11
    _THRESH
    0.09
    家æĹı
    0.09
    ç±»çŃī
    0.09
     subclass
    0.09
    åŃIJç±»
    0.09
    ä½İåĬŁèĢĹ
    0.08
    classify
    0.08
    нÑĤо
    0.08
     FAMILY
    0.08
    Activations Density 0.245%

    No Known Activations