© 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. 9738
    Prev
    Next
    INDEX
    Explanations

    remainder when

    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
    åħ¥åı£å¤Ħ
    -0.07
    èij¬
    -0.07
    åĮºåĨħ
    -0.07
    éªĭ
    -0.07
     Dim
    -0.07
     Kühl
    -0.07
    åĨħå¤ĸ
    -0.07
    olley
    -0.07
     dim
    -0.07
    azel
    -0.06
    POSITIVE LOGITS
    ä½Ļ
    0.10
    remainder
    0.09
     remainder
    0.09
    é¤ĺ
    0.09
    haft
    0.08
    acha
    0.08
    ä½Ļ项
    0.08
    æ®ĭ渣
    0.08
     residue
    0.08
     leftover
    0.08
    Activations Density 0.013%

    No Known Activations