© 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. 10936
    Prev
    Next
    INDEX
    Explanations

    significance and implications

    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
    antar
    -0.08
    符åIJĪæĿ¡ä»¶
    -0.08
    Credentials
    -0.07
     allegedly
    -0.07
    erland
    -0.07
    _credentials
    -0.07
     Credentials
    -0.07
    éĢ¼
    -0.07
    认åĩĨ
    -0.07
    adaan
    -0.07
    POSITIVE LOGITS
     significance
    0.12
    å®ĥ对
    0.11
    çļĦæĦıä¹ī
    0.10
     implications
    0.10
    å®ĥ为
    0.10
    ä½ľçĶ¨åĴĮ
    0.10
    çļĦéĩįè¦ģæĦıä¹ī
    0.09
    çĶ¨å¤Ħ
    0.09
    çİ°å®ŀæĦıä¹ī
    0.09
    çļĦéĩįè¦ģä½ľçĶ¨
    0.09
    Activations Density 0.057%

    No Known Activations