© 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. 48370
    Prev
    Next
    INDEX
    Explanations

    lists, learning, health, crime, anesthesia, estrogen

    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
    (IR
    -0.07
    ouses
    -0.07
    !!:
    -0.06
    apiro
    -0.06
    istributions
    -0.06
    uring
    -0.06
    rames
    -0.06
    ihuah
    -0.06
    (`
    -0.05
    ukul
    -0.05
    POSITIVE LOGITS
    AZE
    0.08
    å¦ĤæѤä¸ĢæĿ¥
    0.07
    è§ģçĬ¶
    0.07
    éĤ£ä¹Ī好
    0.07
    è°ģ说
    0.07
    ä¸İæĮijæĪĺ
    0.07
    çļĦéĩįè¦ģä½ľçĶ¨
    0.07
    omar
    0.07
    çĦ¶å¤§
    0.07
    leden
    0.07
    Activations Density 0.050%

    No Known Activations