© 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. 43045
    Prev
    Next
    INDEX
    Explanations

    life span or duration

    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
    ä¹ĸ
    -0.08
    iri
    -0.08
    åħĪè¡Į
    -0.08
    ophilia
    -0.08
    ervo
    -0.08
    incon
    -0.07
    IDL
    -0.07
    iya
    -0.07
    accessible
    -0.07
    omatik
    -0.07
    POSITIVE LOGITS
    æľĢéķ¿çļĦ
    0.10
    ä¹ħçļĦ
    0.10
    寿åij½
    0.09
    è¾ĥéķ¿çļĦ
    0.09
     longer
    0.09
    å¾ĪçŁŃ
    0.09
    å¾Īéķ¿
    0.09
    -lasting
    0.09
     ago
    0.08
    æľĢéķ¿
    0.08
    Activations Density 0.112%

    No Known Activations