© 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. 21867
    Prev
    Next
    INDEX
    Explanations

    mathematical expression operators

    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
    hnya
    -0.08
    aglio
    -0.08
    æ¯ĴèĽĩ
    -0.08
     prezi
    -0.08
    Unnamed
    -0.08
    ãĤıãģijãģ§
    -0.08
    é»į
    -0.08
    çĶ«
    -0.08
    romise
    -0.08
    à¶Ńà·Ķ
    -0.08
    POSITIVE LOGITS
    ^{
    0.07
     Fin
    0.06
    akk
    0.06
    æŁIJäºĽ
    0.06
    åĽĽ
    0.06
    <|im_end|>
    0.06
     b
    0.06
    åĺīå¹´åįİ
    0.05
    cis
    0.05
     cis
    0.05
    Activations Density 0.087%

    No Known Activations