© 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. 10944
    Prev
    Next
    INDEX
    Explanations

    also, too, either

    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
     però
    -0.08
     however
    -0.08
    пÑĢоÑĩем
    -0.08
    however
    -0.08
     cependant
    -0.07
    anding
    -0.07
     اÙĦبتÙĩ
    -0.07
    æĥ³ä¸įåĪ°
    -0.07
    åĥıä½ł
    -0.07
    åį´ä¹Ł
    -0.07
    POSITIVE LOGITS
    à¸Ńีà¸ģà¸Ķà¹īวย
    0.10
     tampoco
    0.07
    æĽ´åı¯
    0.07
    æĽ´æĺ¯
    0.07
     wast
    0.07
    uver
    0.07
    è¦ģçŁ¥éģĵ
    0.07
    çŃīä¸įèī¯
    0.07
    lix
    0.06
    adder
    0.06
    Activations Density 0.564%

    No Known Activations