© 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. 60221
    Prev
    Next
    INDEX
    Explanations

    name variations like Moses, Carolina, attack

    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
    Patterns
    -0.07
    ä¿¡æģ¯çĶ±
    -0.07
    饵
    -0.07
    èĢĮ代ä¹ĭ
    -0.07
    tep
    -0.07
    erber
    -0.07
    ÏĦÎŃ
    -0.07
     CONV
    -0.07
    над
    -0.07
    ç¡®å®ļäºĨ
    -0.07
    POSITIVE LOGITS
    ä½Ĩåľ¨
    0.07
    å¼ķçĶ³
    0.07
    åħ·æľīçļĦ
    0.07
    بÙĪÙĦ
    0.07
    theit
    0.07
    inian
    0.07
     deje
    0.06
    人æĪĸ
    0.06
     literal
    0.06
    ä¸į符åIJĪ
    0.06
    Activations Density 0.027%

    No Known Activations