© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21484
    Prev
    Next
    INDEX
    Explanations

    completion status

    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
    preserve
    -0.08
     Preserve
    -0.08
     preserved
    -0.07
    pitch
    -0.07
    祸
    -0.07
     preserving
    -0.07
     preserve
    -0.07
    åıijæĮ¥å¥½
    -0.07
    жай
    -0.07
    æıIJä¾ĽæĽ´å¤ļ
    -0.07
    POSITIVE LOGITS
     completion
    0.13
    å®ĮæĪIJäºĨ
    0.12
    å®ĮæĪIJæĥħåĨµ
    0.12
     accomplishment
    0.12
     Completion
    0.12
    åľ°å®ĮæĪIJ
    0.11
    å®ĮæĪIJçļĦ
    0.11
     satisfactory
    0.11
     assurance
    0.11
    è¾¾æłĩ
    0.11
    Activations Density 0.229%

    No Known Activations