© 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. 19262
    Prev
    Next
    INDEX
    Explanations

    confirmed expectation

    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
    渡åģĩ
    -0.08
    åĬ¡
    -0.08
    å¹²åĺĽ
    -0.07
    åĭĻ
    -0.07
    اراÙĨ
    -0.07
    vain
    -0.07
    ì±Ħ
    -0.07
    encers
    -0.07
    èıģ
    -0.07
    baugh
    -0.07
    POSITIVE LOGITS
    ç¡®å®ŀ
    0.09
    ç¡®å®ŀæĺ¯
    0.09
     indeed
    0.09
    æŀľçľŁ
    0.08
    確實
    0.08
    確ãģĭãģ«
    0.07
    çļĦç¡®æĺ¯
    0.07
    лива
    0.07
    ongs
    0.07
    æŀľçĦ¶æĺ¯
    0.06
    Activations Density 0.009%

    No Known Activations