© 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. 51595
    Prev
    Next
    INDEX
    Explanations

    alienate, exclude, isolate

    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
    ç³Ĭæ¶Ĥ
    -0.06
    iane
    -0.06
    úa
    -0.06
    urg
    -0.06
    ua
    -0.06
    ä¸įè¡°
    -0.06
     expended
    -0.06
     entrusted
    -0.05
    çĶ·åĦ¿
    -0.05
    WT
    -0.05
    POSITIVE LOGITS
    éļĶç»Ŀ
    0.11
     khá»ıi
    0.11
     biá»ĩt
    0.09
    éļĶ离
    0.09
    olate
    0.09
    离
    0.09
    éĽ¢
    0.09
     isolation
    0.09
    è§ĴèIJ½
    0.09
    éļĶéĽ¢
    0.09
    Activations Density 0.078%

    No Known Activations