© 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. 2329
    Prev
    Next
    INDEX
    Explanations

    image filenames or asset scaling

    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
    en
    -0.08
    ×Ļ×Ŀ
    -0.08
    UGH
    -0.07
    sium
    -0.07
    eschi
    -0.07
     ()->
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
     оÑĩеÑĢ
    -0.07
    []"
    -0.07
    POSITIVE LOGITS
    å·¦åı³çļĦ
    0.10
    ä¹ĭå¤ļ
    0.10
    æĪĸ以ä¸Ĭ
    0.09
    以åĨħçļĦ
    0.09
    次çļĦ
    0.09
    以ä¸ĬçļĦ
    0.09
    åıĬ以ä¸ĬçļĦ
    0.08
    以ä¸Ĭæĺ¯
    0.08
    åıĬ以ä¸Ĭ
    0.08
    以ä¸ĭçļĦ
    0.08
    Activations Density 0.004%

    No Known Activations