© 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. 49861
    Prev
    Next
    INDEX
    Explanations

    chemical reaction suffixes

    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
    ful
    -0.08
    åĴĮ家人
    -0.08
    voud
    -0.08
    åĴĮæĸ¹æ³ķ
    -0.07
    less
    -0.07
    æĢ§å·¥ä½ľ
    -0.07
    loom
    -0.07
    lessly
    -0.07
    fulness
    -0.07
    aurant
    -0.07
    POSITIVE LOGITS
     ulang
    0.09
    /rest
    0.08
    à§įথ
    0.08
    /trans
    0.08
    ally
    0.07
    andia
    0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.07
    /am
    0.07
    laud
    0.07
    feo
    0.07
    Activations Density 0.032%

    No Known Activations