© 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. 34027
    Prev
    Next
    INDEX
    Explanations

    asking "why"

    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
    -redux
    -0.07
    ogn
    -0.07
    ohner
    -0.07
    indh
    -0.07
     zb
    -0.07
    èľĤçªĿ
    -0.07
    Ñĸм
    -0.07
    cca
    -0.07
    elin
    -0.07
    ÑĥдаÑĢ
    -0.06
    POSITIVE LOGITS
    ói
    0.07
    çIJĨçĶ±
    0.07
    ãĥŁãĥ³ãĤ°
    0.07
    说æĺİ
    0.07
    åĺĪ
    0.07
    è¹ĭ
    0.07
    ocode
    0.07
    ao
    0.07
    漪
    0.06
    ä¾Ŀæį®
    0.06
    Activations Density 0.028%

    No Known Activations