© 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. 33180
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives

    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
    erer
    -0.09
    erat
    -0.08
    sWith
    -0.08
    áss
    -0.08
    eri
    -0.08
    arat
    -0.08
    anita
    -0.08
    à§įড
    -0.08
    ÃŁ
    -0.08
    arb
    -0.08
    POSITIVE LOGITS
    -ever
    0.15
    ablish
    0.14
    åĴĮæľĢ
    0.12
    åĴĮ第äºĮ
    0.09
    ä¹Łæĺ¯æľĢ
    0.09
    -vous
    0.09
    /sm
    0.09
    -known
    0.09
    -than
    0.09
     among
    0.08
    Activations Density 0.063%

    No Known Activations