© 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. 14060
    Prev
    Next
    INDEX
    Explanations

    conditioning regimens

    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
    ually
    -0.08
    aspers
    -0.08
    pecific
    -0.08
    ä¸įèĥľæķ°
    -0.08
    åĴĮæĸ¹æ³ķ
    -0.08
    .rules
    -0.08
    icularly
    -0.08
    çļĦæľīåħ³è§Ħå®ļ
    -0.08
    /items
    -0.08
    è¶Ĭèµ°
    -0.08
    POSITIVE LOGITS
    è¡«
    0.07
    读çī©
    0.06
    æĸĩ件
    0.06
    ฯ
    0.06
    åĵģ
    0.06
    åĩ½æķ°
    0.06
    ÛĮÙĩ
    0.06
    件
    0.06
    åŃĹæł·
    0.06
    ç©´
    0.06
    Activations Density 1.448%

    No Known Activations