© 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. 20830
    Prev
    Next
    INDEX
    Explanations

    integer boundaries and overflow

    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
    atlan
    -0.08
    æĭĸ
    -0.07
    纽
    -0.07
    èĬ±ä¸Ģ
    -0.07
     наÑģÑĤÑĢо
    -0.07
    ανο
    -0.06
    াস
    -0.06
    èĩ³å°Ĭ
    -0.06
     Porr
    -0.06
    drag
    -0.06
    POSITIVE LOGITS
    累积
    0.08
    äck
    0.08
     sums
    0.08
    é¢ĦæľŁ
    0.08
     expected
    0.07
     аккÑĥ
    0.07
    è¶ħåĩºäºĨ
    0.07
     prevision
    0.07
    ngen
    0.07
     rued
    0.07
    Activations Density 0.010%

    No Known Activations