© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2619
    Prev
    Next
    INDEX
    Explanations

    modulo and remainder calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hti
    -0.26
    estruct
    -0.25
    代åĬŀ
    -0.23
    _TYP
    -0.23
    ç½ķè§ģ
    -0.23
    åĽ½éĻħåIJĪä½ľ
    -0.23
    à¹īà¸ĩ
    -0.23
    ubo
    -0.23
    é¦Ļæ°´
    -0.23
    .dispatch
    -0.22
    POSITIVE LOGITS
    0.29
    IMUM
    0.25
    ulo
    0.24
     dec
    0.23
     Preserve
    0.23
    æĻ·
    0.23
     conversation
    0.23
    ulos
    0.23
     Mahar
    0.22
    ometer
    0.22
    Activations Density 0.224%

    No Known Activations