© 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. 28939
    Prev
    Next
    INDEX
    Explanations

    purpose, point, intended

    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
    icher
    -0.08
    enf
    -0.07
    å¤įæĿĤçļĦ
    -0.07
    å½±åĵįåĽłç´ł
    -0.07
    |-
    -0.07
    soon
    -0.07
    å½±åĵįåĪ°
    -0.07
    ä¼ļåIJİ
    -0.07
    hawks
    -0.06
    bé
    -0.06
    POSITIVE LOGITS
    çļĦæł¸å¿ĥ
    0.11
     purpose
    0.10
    æł¸å¿ĥä»·åĢ¼
    0.10
     core
    0.10
    raison
    0.10
    ç²¾é«ĵ
    0.09
    缮çļĦå°±æĺ¯
    0.09
    å°±æĺ¯è¦ģ
    0.09
    æł¸å¿ĥ
    0.09
     essence
    0.09
    Activations Density 0.088%

    No Known Activations