© 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. 10645
    Prev
    Next
    INDEX
    Explanations

    suckling period, pulmonate snails, retina-ready, crossover detection, strict mode

    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
    åı¯æĥ³
    -0.10
    ãĥªãĤ¨
    -0.09
    kens
    -0.09
    ாள
    -0.09
    缸åħ³æݨèįIJ
    -0.09
    erstand
    -0.09
    ioms
    -0.09
    çī¹æľĹ
    -0.08
    çijŀæĭī
    -0.08
    ìĬ¤íģ¬
    -0.08
    POSITIVE LOGITS
    ãĢģ
    0.07
    /
    0.07
    æĪĸ
    0.06
    ãĢįãĢģãĢĮ
    0.06
     ↵
    0.06
     or
    0.06
      ↵
    0.06
    ãĢįãĢģ
    0.06
    åĴĮ
    0.06
    -
    0.05
    Activations Density 0.531%

    No Known Activations