© 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. 21641
    Prev
    Next
    INDEX
    Explanations

    remove gaps or delete elements

    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
    ä¸Ŀ
    -0.08
    ä¸ĿçļĦ
    -0.08
    åĪļåĪļå¼Ģå§ĭ
    -0.07
    exas
    -0.07
    /cs
    -0.07
    -parser
    -0.07
    æī«çłģåħ³æ³¨
    -0.07
    itere
    -0.07
    borne
    -0.07
    Exclusive
    -0.07
    POSITIVE LOGITS
    åĪłéĻ¤
    0.10
    (delete
    0.09
     deletion
    0.09
    .delete
    0.08
    .Delete
    0.08
     Delete
    0.08
    .RemoveAt
    0.08
    移éĻ¤
    0.08
     delete
    0.08
     removal
    0.08
    Activations Density 0.016%

    No Known Activations