© 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. 45931
    Prev
    Next
    INDEX
    Explanations

    afferent nerve connections

    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
     certified
    -0.06
     convenc
    -0.06
    èĩ
    -0.06
     practic
    -0.06
     testament
    -0.06
     lifes
    -0.06
    uman
    -0.06
    å°Ĩå°±
    -0.06
     cases
    -0.06
     hay
    -0.06
    POSITIVE LOGITS
    onton
    0.09
    çݰ代æľįåĬ¡ä¸ļ
    0.08
    Gate
    0.08
     arcade
    0.08
    æĬķå°Ħ
    0.08
    ä¾Ĩèĩª
    0.08
    archical
    0.08
    agger
    0.08
     orchestrated
    0.08
     neuro
    0.08
    Activations Density 0.169%

    No Known Activations