© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62062
    Prev
    Next
    INDEX
    Explanations

    importance and relevance

    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
     therefore
    -0.08
     dunque
    -0.07
     hierbei
    -0.07
    ãĥ¬ãĥ«
    -0.07
    ä»»åĬ¡æĺ¯
    -0.07
    менов
    -0.07
     thus
    -0.07
    åĽłæѤ
    -0.07
    orry
    -0.07
    è¿Ļæł·çļĦ
    -0.07
    POSITIVE LOGITS
     relevant
    0.08
    人ä¹ĭ
    0.07
    relevant
    0.07
    å¤ļæķ°äºº
    0.07
    大å¤ļæķ°äºº
    0.07
    successful
    0.07
    大éĥ¨åĪĨ人
    0.07
     baÄŁ
    0.06
    amon
    0.06
    å°
    0.06
    Activations Density 0.058%

    No Known Activations