© 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. 21871
    Prev
    Next
    INDEX
    Explanations

    range, band, table size, park, link, dark, barrel, series finale

    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
    çļĦåŃ£èĬĤ
    -0.07
    ¦
    -0.07
    ambu
    -0.06
     Jour
    -0.06
    sell
    -0.06
    äºİè¡Į
    -0.06
     sinn
    -0.06
     aller
    -0.06
     Riley
    -0.06
     Vis
    -0.06
    POSITIVE LOGITS
    èµ·çĤ¹
    0.11
    ä¸Ńå¿ĥçŃī
    0.10
    èµ·å§ĭ
    0.10
    第ä¸Ģä½į
    0.10
     midpoint
    0.10
    é¦ĸä½į
    0.10
    ä¸Ńå¿ĥ
    0.10
     شرÙĪع
    0.09
     center
    0.09
    ä¸Ńéĥ¨
    0.09
    Activations Density 0.232%

    No Known Activations