© 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. 8991
    Prev
    Next
    INDEX
    Explanations

    noun followed by preposition

    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
    çĭ
    -0.08
    对该
    -0.07
     afterward
    -0.06
    endale
    -0.06
    缸
    -0.06
    é¾Ļå±±
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    Äĵja
    -0.06
    ilus
    -0.06
     ausges
    -0.05
    POSITIVE LOGITS
    çļĦ缸åħ³åĨħ容
    0.09
    ç®ĹäºĨ
    0.08
    ä¸įå¾Ĺä¸į说
    0.08
    ä¹ĭç±»
    0.08
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    0.08
    类似éĹ®é¢ĺ
    0.07
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    ócios
    0.07
    /rec
    0.07
    >>::
    0.07
    Activations Density 0.628%

    No Known Activations