© 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. 45790
    Prev
    Next
    INDEX
    Explanations

    common nouns in context

    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
     übrigens
    -0.14
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.12
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.12
     inilah
    -0.09
    éķ¿è¶³
    -0.09
    åĽ¾åĨĮ
    -0.09
    ä¸įæĺ¯è¯´
    -0.09
    ×ķ×ķת
    -0.09
    æĸ°æµªç½ij
    -0.09
    åħļæĢ»æĶ¯ä¹¦è®°
    -0.09
    POSITIVE LOGITS
    \n
    0.12
     ___
    0.11
    \"
    0.11
    ____
    0.10
    ...
    0.10
     [...]
    0.10
     \"
    0.10
     ______
    0.09
     ...
    0.09
    âĢ
    0.09
    Activations Density 0.531%

    No Known Activations