© 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. 17994
    Prev
    Next
    INDEX
    Explanations

    thanks in advance

    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
    unched
    -0.07
    давно
    -0.07
     lately
    -0.07
    .generator
    -0.07
    åĪĿè§ģ
    -0.07
    æĹ¢çĦ¶æĺ¯
    -0.07
    Õ¤
    -0.06
    æľ¬æĬ¥è®¯
    -0.06
    èĢĮèµ·
    -0.06
    æĹ¢çĦ¶
    -0.06
    POSITIVE LOGITS
    auce
    0.10
    æĮĩçĤ¹
    0.09
    彦
    0.07
    æĮĩæķĻ
    0.07
    åı¯ä»¥å¸®åĬ©
    0.07
    缸åĬ©
    0.07
    à¸Īร
    0.07
    ombo
    0.07
    åIJĦè·¯
    0.07
     onFailure
    0.07
    Activations Density 0.626%

    No Known Activations