© 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. 32498
    Prev
    Next
    INDEX
    Explanations

    math sums and calculations

    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
    欲滴
    -0.07
     Ouro
    -0.07
    mailto
    -0.07
    åĭ¾åĭĴåĩº
    -0.07
    OrCreate
    -0.07
    Ñįй
    -0.07
    entren
    -0.07
    .Enum
    -0.07
     Diri
    -0.07
    éŁŃ
    -0.06
    POSITIVE LOGITS
    è¿IJç®Ĺ
    0.12
     arithmetic
    0.12
    ç»ĵæŀľä¸º
    0.10
    ç®Ĺæľ¯
    0.10
     calculation
    0.10
     multiplication
    0.09
    ç»ĵæŀľçļĦ
    0.09
     Arithmetic
    0.09
    æī§è¡ĮçļĦ
    0.09
    ä¹ĺæ³ķ
    0.09
    Activations Density 0.075%

    No Known Activations