© 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. 33768
    Prev
    Next
    INDEX
    Explanations

    interactions, messages, neuropeptides

    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
     reverted
    -0.06
     initially
    -0.06
     ↵
    -0.06
    T
    -0.06
    ãĤĦãĤĦ
    -0.06
    oretical
    -0.06
    ad
    -0.06
    ·
    -0.05
    æĦŁåıĹ
    -0.05
     somewhat
    -0.05
    POSITIVE LOGITS
    æľĢåĢ¼å¾Ĺ
    0.09
    ripp
    0.09
    缮çļĦå°±æĺ¯
    0.09
    èĢĮä¸įè§ģ
    0.08
    eldet
    0.08
     Ñģиг
    0.08
    èĢĮä¸įæĺ¯
    0.08
    ä¿¡åĩ½
    0.08
    arden
    0.08
    LEGRO
    0.08
    Activations Density 0.010%

    No Known Activations