© 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. 30715
    Prev
    Next
    INDEX
    Explanations

    lease", "distinction", "intent"

    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
    urch
    -0.07
     enig
    -0.07
    .truth
    -0.07
     Experiment
    -0.07
    ä¹ŁæĮº
    -0.06
     newest
    -0.06
    è¿Ļ个æķ°åŃĹ
    -0.06
    sia
    -0.06
    æĮº
    -0.06
    åģ¥
    -0.06
    POSITIVE LOGITS
    认å®ļ为
    0.10
    æĦıåĽ¾
    0.10
     distinction
    0.09
     intent
    0.09
    ä¸įæŀĦæĪIJ
    0.09
    åĮºåĪĨ
    0.09
    åĪĨä¸įæ¸ħ
    0.08
    çļĦåĮºåĪ«
    0.08
    åĪĴ
    0.08
    Intent
    0.08
    Activations Density 0.025%

    No Known Activations