© 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. 39251
    Prev
    Next
    INDEX
    Explanations

    spitzer jennifer hom non

    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
    acara
    -0.08
    itesse
    -0.08
    _FC
    -0.08
    astia
    -0.08
    ¹
    -0.08
     diur
    -0.08
    身æĿIJ
    -0.07
    æĭŃ缮
    -0.07
    itale
    -0.07
    ä¾Ŀ次为
    -0.07
    POSITIVE LOGITS
    åij¨åĽ´
    0.07
    ende
    0.07
    å±Ģ
    0.06
     Sr
    0.06
     prot
    0.06
     lod
    0.06
     buc
    0.06
    imit
    0.06
     Qin
    0.06
    æű
    0.06
    Activations Density 0.001%

    No Known Activations