© 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. 20662
    Prev
    Next
    INDEX
    Explanations

    FS, em, mm

    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
    nga
    -0.09
    æĹ¢
    -0.06
    ((&
    -0.06
    è¼
    -0.06
    æ©
    -0.06
    åĶ
    -0.06
     ÑħодÑĥ
    -0.06
     одна
    -0.05
    æĹ
    -0.05
     ns
    -0.05
    POSITIVE LOGITS
    çļĦåħ¶ä»ĸ
    0.11
     demás
    0.11
    åħ¶ä»ĸçļĦ
    0.10
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.10
    åħ¶å®ĥçļĦ
    0.10
    other
    0.09
    çļĦè¿ĺæľī
    0.09
     other
    0.09
    èĢĮéĻį
    0.09
    åħ¶ä»ĸ
    0.09
    Activations Density 0.080%

    No Known Activations