© 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. 17947
    Prev
    Next
    INDEX
    Explanations

    removing or deleting items

    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
     tersendiri
    -0.07
    ä¸įåIJĮçļĦ人
    -0.07
    -0.07
    uters
    -0.07
    eries
    -0.07
    çļĦæľĢæĸ°
    -0.07
    æĸ°ä¸Ģå±Ĭ
    -0.07
    arpa
    -0.07
    åħ¶è§ĤçĤ¹
    -0.06
    uron
    -0.06
    POSITIVE LOGITS
     bỼt
    0.15
     лиÑĪ
    0.13
    å¤ļä½Ļ
    0.12
    å¤ļä½ĻçļĦ
    0.12
    (remove
    0.12
     лиÑĪниÑħ
    0.12
    /remove
    0.11
    æİīäºĨ
    0.11
    æĪĸåĪłéĻ¤
    0.11
    æİī
    0.10
    Activations Density 0.137%

    No Known Activations